Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3896 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3673. Min Range: -4.3673
Max Act: 4.3673. Min Act: -0.1700
Data Index: 4752213 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3673. Min Range: -4.3673
Max Act: 4.2110. Min Act: -0.1700
Data Index: 7828617 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3673. Min Range: -4.3673
Max Act: 4.1485. Min Act: -0.1700
Data Index: 8760941 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3673. Min Range: -4.3673
Max Act: 4.1485. Min Act: -0.1700
Data Index: 1501021 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3673. Min Range: -4.3673
Max Act: 4.1173. Min Act: -0.1700
Data Index: 2378398 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3673. Min Range: -4.3673
Max Act: 4.0860. Min Act: -0.1700
Data Index: 29504 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3673. Min Range: -4.3673
Max Act: 4.0860. Min Act: -0.1700
Data Index: 2025885 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3673. Min Range: -4.3673
Max Act: 4.0235. Min Act: -0.1700
Data Index: 7891259 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3673. Min Range: -4.3673
Max Act: 4.0235. Min Act: -0.1700
Data Index: 7874494 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3673. Min Range: -4.3673
Max Act: 4.0235. Min Act: -0.1700
Data Index: 2048193 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3673. Min Range: -4.3673
Max Act: 4.0235. Min Act: -0.1700
Data Index: 6617332 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3673. Min Range: -4.3673
Max Act: 4.0235. Min Act: -0.1700
Data Index: 6629533 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3673. Min Range: -4.3673
Max Act: 3.9922. Min Act: -0.1700
Data Index: 1948826 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3673. Min Range: -4.3673
Max Act: 3.9922. Min Act: -0.1700
Data Index: 6072769 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3673. Min Range: -4.3673
Max Act: 3.9610. Min Act: -0.1700
Data Index: 8249945 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3673. Min Range: -4.3673
Max Act: 3.9297. Min Act: -0.1700
Data Index: 4113631 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3673. Min Range: -4.3673
Max Act: 3.9610. Min Act: -0.1700
Data Index: 6081662 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3673. Min Range: -4.3673
Max Act: 3.9922. Min Act: -0.1700
Data Index: 8561312 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3673. Min Range: -4.3673
Max Act: 3.9297. Min Act: -0.1700
Data Index: 3537334 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3673. Min Range: -4.3673
Max Act: 3.9297. Min Act: -0.1700
Data Index: 3259260 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19