Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.9110. Min Act: -0.1700
Data Index: 397091 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.8485. Min Act: -0.1700
Data Index: 6875918 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.8173. Min Act: -0.1700
Data Index: 5012808 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.7548. Min Act: -0.1700
Data Index: 5094533 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.7235. Min Act: -0.1700
Data Index: 6861028 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.5985. Min Act: -0.1700
Data Index: 3453956 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.6610. Min Act: -0.1700
Data Index: 1810773 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.6298. Min Act: -0.1700
Data Index: 4610020 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.6298. Min Act: -0.1700
Data Index: 3292964 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.5985. Min Act: -0.1700
Data Index: 8082856 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.5673. Min Act: -0.1700
Data Index: 5441846 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.5673. Min Act: -0.1700
Data Index: 2341462 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.5985. Min Act: -0.1700
Data Index: 5295633 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.5673. Min Act: -0.1700
Data Index: 5403953 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.5673. Min Act: -0.1700
Data Index: 5054765 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.5673. Min Act: -0.1700
Data Index: 2793070 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.5360. Min Act: -0.1700
Data Index: 695888 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.5360. Min Act: -0.1700
Data Index: 894180 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.5048. Min Act: -0.1700
Data Index: 1432157 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9110. Min Range: -5.9110
Max Act: 5.5048. Min Act: -0.1700
Data Index: 5341365 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19