Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5465 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0311. Min Range: -5.0311
Max Act: 5.0311. Min Act: -0.1700
Data Index: 563634 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.8748. Min Act: -0.1700
Data Index: 3236340 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.8748. Min Act: -0.1700
Data Index: 7095296 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.8748. Min Act: -0.1700
Data Index: 4385602 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.8436. Min Act: -0.1700
Data Index: 2198343 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.8436. Min Act: -0.1700
Data Index: 5042615 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.8123. Min Act: -0.1700
Data Index: 5215770 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.8123. Min Act: -0.1700
Data Index: 3646192 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.8123. Min Act: -0.1700
Data Index: 6304974 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.7811. Min Act: -0.1700
Data Index: 5650137 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.7811. Min Act: -0.1700
Data Index: 1543866 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.7498. Min Act: -0.1700
Data Index: 5984771 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.7498. Min Act: -0.1700
Data Index: 7993689 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.7498. Min Act: -0.1700
Data Index: 6060981 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.7186. Min Act: -0.1700
Data Index: 7241740 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.7186. Min Act: -0.1700
Data Index: 2444944 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.7186. Min Act: -0.1700
Data Index: 3285261 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.7186. Min Act: -0.1700
Data Index: 7946585 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.6873. Min Act: -0.1700
Data Index: 6758376 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0311. Min Range: -5.0311
Max Act: 4.6873. Min Act: -0.1700
Data Index: 1274387 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19