Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3129 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.4320. Min Act: -0.1700
Data Index: 1288529 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.4320. Min Act: -0.1700
Data Index: 6379 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3695. Min Act: -0.1700
Data Index: 8251308 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3695. Min Act: -0.1700
Data Index: 4952767 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3383. Min Act: -0.1700
Data Index: 4765270 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3383. Min Act: -0.1700
Data Index: 1456341 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3383. Min Act: -0.1700
Data Index: 6456069 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3383. Min Act: -0.1700
Data Index: 5103099 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3383. Min Act: -0.1700
Data Index: 6691274 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3383. Min Act: -0.1700
Data Index: 8572636 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3383. Min Act: -0.1700
Data Index: 8051006 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3383. Min Act: -0.1700
Data Index: 8023756 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3383. Min Act: -0.1700
Data Index: 2013653 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3070. Min Act: -0.1700
Data Index: 543863 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3070. Min Act: -0.1700
Data Index: 4176324 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3070. Min Act: -0.1700
Data Index: 362310 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3070. Min Act: -0.1700
Data Index: 5273391 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3070. Min Act: -0.1700
Data Index: 6328518 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3070. Min Act: -0.1700
Data Index: 6454154 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4320. Min Range: -4.4320
Max Act: 4.3383. Min Act: -0.1700
Data Index: 6680089 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19