Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4187 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3283. Min Range: -8.3283
Max Act: 8.3283. Min Act: -0.1700
Data Index: 3175644 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3283. Min Range: -8.3283
Max Act: 8.0783. Min Act: -0.1700
Data Index: 3806317 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3283. Min Range: -8.3283
Max Act: 8.0158. Min Act: -0.1700
Data Index: 8402980 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.9533. Min Act: -0.1700
Data Index: 1717306 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3283. Min Range: -8.3283
Max Act: 8.0158. Min Act: -0.1700
Data Index: 6128551 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.8908. Min Act: -0.1700
Data Index: 8414965 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.8908. Min Act: -0.1700
Data Index: 8062316 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.8908. Min Act: -0.1700
Data Index: 7496127 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.8908. Min Act: -0.1700
Data Index: 7185681 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.8283. Min Act: -0.1700
Data Index: 0 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.7658. Min Act: -0.1700
Data Index: 3372430 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.7033. Min Act: -0.1700
Data Index: 7311139 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.6720. Min Act: -0.1700
Data Index: 2338282 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.6408. Min Act: -0.1700
Data Index: 4224391 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.6408. Min Act: -0.1700
Data Index: 3565939 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.6408. Min Act: -0.1700
Data Index: 1985913 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.6408. Min Act: -0.1700
Data Index: 5833062 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.6408. Min Act: -0.1700
Data Index: 8472816 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.6408. Min Act: -0.1700
Data Index: 883247 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3283. Min Range: -8.3283
Max Act: 7.6095. Min Act: -0.1700
Data Index: 6314101 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19