Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2693 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.0240. Min Range: -17.0240
Max Act: 17.0240. Min Act: -0.1700
Data Index: 5255169 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.0240. Min Range: -17.0240
Max Act: 16.8990. Min Act: -0.1700
Data Index: 3680137 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.0240. Min Range: -17.0240
Max Act: 16.5240. Min Act: -0.1700
Data Index: 3148997 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.0240. Min Range: -17.0240
Max Act: 16.3990. Min Act: -0.1700
Data Index: 1546603 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.0240. Min Range: -17.0240
Max Act: 16.2740. Min Act: -0.1700
Data Index: 8177414 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.0240. Min Range: -17.0240
Max Act: 16.1490. Min Act: -0.1700
Data Index: 3149153 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.0240. Min Range: -17.0240
Max Act: 16.1490. Min Act: -0.1700
Data Index: 8691571 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.0240. Min Range: -17.0240
Max Act: 16.0240. Min Act: -0.1700
Data Index: 6826676 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.0240. Min Range: -17.0240
Max Act: 16.0240. Min Act: -0.1700
Data Index: 3605609 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.0240. Min Range: -17.0240
Max Act: 15.8990. Min Act: -0.1700
Data Index: 1232341 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.0240. Min Range: -17.0240
Max Act: 16.0240. Min Act: -0.1700
Data Index: 5668263 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.0240. Min Range: -17.0240
Max Act: 15.8990. Min Act: -0.1700
Data Index: 603929 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.0240. Min Range: -17.0240
Max Act: 16.0240. Min Act: -0.1700
Data Index: 2004347 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.0240. Min Range: -17.0240
Max Act: 15.8990. Min Act: -0.1700
Data Index: 2943792 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.0240. Min Range: -17.0240
Max Act: 15.8990. Min Act: -0.1700
Data Index: 4656910 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.0240. Min Range: -17.0240
Max Act: 15.8990. Min Act: -0.1700
Data Index: 2088553 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.0240. Min Range: -17.0240
Max Act: 15.8990. Min Act: -0.1700
Data Index: 1417507 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.0240. Min Range: -17.0240
Max Act: 15.8990. Min Act: -0.1700
Data Index: 7614747 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.0240. Min Range: -17.0240
Max Act: 15.8990. Min Act: -0.1700
Data Index: 7126676 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.0240. Min Range: -17.0240
Max Act: 15.8990. Min Act: -0.1700
Data Index: 1715097 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19