Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4871 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.7228. Min Act: -0.1700
Data Index: 3978447 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.6290. Min Act: -0.1700
Data Index: 514607 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.5978. Min Act: -0.1700
Data Index: 4639977 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.5978. Min Act: -0.1700
Data Index: 891377 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.5665. Min Act: -0.1700
Data Index: 412186 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.5353. Min Act: -0.1700
Data Index: 2044250 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.4728. Min Act: -0.1700
Data Index: 7556135 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.4728. Min Act: -0.1700
Data Index: 59835 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.4728. Min Act: -0.1700
Data Index: 6956234 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.4728. Min Act: -0.1700
Data Index: 1899335 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.4415. Min Act: -0.1700
Data Index: 8520138 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.4415. Min Act: -0.1700
Data Index: 3947116 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.4415. Min Act: -0.1700
Data Index: 415782 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.4103. Min Act: -0.1700
Data Index: 6298927 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.3790. Min Act: -0.1700
Data Index: 6807706 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.3790. Min Act: -0.1700
Data Index: 6541452 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.3790. Min Act: -0.1700
Data Index: 4506480 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.3165. Min Act: -0.1700
Data Index: 4192179 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.3165. Min Act: -0.1700
Data Index: 6168170 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7228. Min Range: -7.7228
Max Act: 7.2853. Min Act: -0.1700
Data Index: 3215483 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19