Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5684 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.8492. Min Act: -0.1700
Data Index: 1058002 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.6617. Min Act: -0.1700
Data Index: 3770571 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.6304. Min Act: -0.1700
Data Index: 549568 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.5992. Min Act: -0.1700
Data Index: 1681795 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.5992. Min Act: -0.1700
Data Index: 3394004 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.5679. Min Act: -0.1700
Data Index: 7128467 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.5367. Min Act: -0.1700
Data Index: 4395967 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.5367. Min Act: -0.1700
Data Index: 3065876 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.5367. Min Act: -0.1700
Data Index: 7629225 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.5367. Min Act: -0.1700
Data Index: 8178169 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.5367. Min Act: -0.1700
Data Index: 8067057 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.5054. Min Act: -0.1700
Data Index: 3761044 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.5054. Min Act: -0.1700
Data Index: 8399202 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.5054. Min Act: -0.1700
Data Index: 6164424 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.5054. Min Act: -0.1700
Data Index: 5571126 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.5054. Min Act: -0.1700
Data Index: 3648814 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.4742. Min Act: -0.1700
Data Index: 5139859 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.4742. Min Act: -0.1700
Data Index: 778189 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.4742. Min Act: -0.1700
Data Index: 5709290 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8492. Min Range: -4.8492
Max Act: 4.4742. Min Act: -0.1700
Data Index: 3424740 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19