Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5984. Min Range: -8.5984
Max Act: 8.5984. Min Act: -0.1700
Data Index: 8511801 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5984. Min Range: -8.5984
Max Act: 8.4734. Min Act: -0.1700
Data Index: 8672499 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5984. Min Range: -8.5984
Max Act: 8.4109. Min Act: -0.1700
Data Index: 6728443 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5984. Min Range: -8.5984
Max Act: 8.3484. Min Act: -0.1700
Data Index: 3795203 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5984. Min Range: -8.5984
Max Act: 8.1609. Min Act: -0.1700
Data Index: 4982603 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5984. Min Range: -8.5984
Max Act: 8.1609. Min Act: -0.1700
Data Index: 7425850 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5984. Min Range: -8.5984
Max Act: 8.0984. Min Act: -0.1700
Data Index: 646246 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5984. Min Range: -8.5984
Max Act: 8.0984. Min Act: -0.1700
Data Index: 2007383 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5984. Min Range: -8.5984
Max Act: 8.0984. Min Act: -0.1700
Data Index: 314922 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5984. Min Range: -8.5984
Max Act: 8.0359. Min Act: -0.1700
Data Index: 421200 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5984. Min Range: -8.5984
Max Act: 8.0359. Min Act: -0.1700
Data Index: 1694806 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5984. Min Range: -8.5984
Max Act: 8.0359. Min Act: -0.1700
Data Index: 7482414 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5984. Min Range: -8.5984
Max Act: 8.0359. Min Act: -0.1700
Data Index: 1931465 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5984. Min Range: -8.5984
Max Act: 7.9734. Min Act: -0.1700
Data Index: 5694382 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5984. Min Range: -8.5984
Max Act: 7.9734. Min Act: -0.1700
Data Index: 2311680 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5984. Min Range: -8.5984
Max Act: 7.9734. Min Act: -0.1700
Data Index: 4312380 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5984. Min Range: -8.5984
Max Act: 7.9734. Min Act: -0.1700
Data Index: 845059 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5984. Min Range: -8.5984
Max Act: 7.9109. Min Act: -0.1700
Data Index: 2009480 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5984. Min Range: -8.5984
Max Act: 7.8484. Min Act: -0.1700
Data Index: 8284228 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5984. Min Range: -8.5984
Max Act: 7.8484. Min Act: -0.1700
Data Index: 3406684 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19