Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4672 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.6857. Min Act: -0.1700
Data Index: 6108326 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.4357. Min Act: -0.1700
Data Index: 4301913 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.3732. Min Act: -0.1700
Data Index: 3872980 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.2482. Min Act: -0.1700
Data Index: 3676420 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.3107. Min Act: -0.1700
Data Index: 5360150 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.2482. Min Act: -0.1700
Data Index: 3528359 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.2482. Min Act: -0.1700
Data Index: 6061303 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.1232. Min Act: -0.1700
Data Index: 6499169 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.1857. Min Act: -0.1700
Data Index: 1513506 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.1232. Min Act: -0.1700
Data Index: 5529780 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.1232. Min Act: -0.1700
Data Index: 2302220 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.1232. Min Act: -0.1700
Data Index: 5615130 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.1857. Min Act: -0.1700
Data Index: 5699376 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.1232. Min Act: -0.1700
Data Index: 5776951 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.0607. Min Act: -0.1700
Data Index: 7987531 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6857. Min Range: -12.6857
Max Act: 12.0607. Min Act: -0.1700
Data Index: 2707861 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6857. Min Range: -12.6857
Max Act: 11.9982. Min Act: -0.1700
Data Index: 3461300 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6857. Min Range: -12.6857
Max Act: 11.9982. Min Act: -0.1700
Data Index: 4689712 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6857. Min Range: -12.6857
Max Act: 11.9982. Min Act: -0.1700
Data Index: 2545059 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6857. Min Range: -12.6857
Max Act: 11.9357. Min Act: -0.1700
Data Index: 7846066 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19