Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3537 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1902. Min Range: -7.1902
Max Act: 7.1902. Min Act: -0.1700
Data Index: 4115248 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.8777. Min Act: -0.1700
Data Index: 7013124 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.8464. Min Act: -0.1700
Data Index: 2484246 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.7839. Min Act: -0.1700
Data Index: 1745161 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.7527. Min Act: -0.1700
Data Index: 203344 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.7527. Min Act: -0.1700
Data Index: 2280463 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.7527. Min Act: -0.1700
Data Index: 2185923 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.7214. Min Act: -0.1700
Data Index: 3143339 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.7214. Min Act: -0.1700
Data Index: 7059915 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.6902. Min Act: -0.1700
Data Index: 6426255 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.6589. Min Act: -0.1700
Data Index: 5892656 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.6277. Min Act: -0.1700
Data Index: 1706883 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.5964. Min Act: -0.1700
Data Index: 4083229 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.5964. Min Act: -0.1700
Data Index: 5946680 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.5964. Min Act: -0.1700
Data Index: 4288498 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.5652. Min Act: -0.1700
Data Index: 1059273 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.5652. Min Act: -0.1700
Data Index: 3517450 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.5027. Min Act: -0.1700
Data Index: 6307758 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.5027. Min Act: -0.1700
Data Index: 8445200 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1902. Min Range: -7.1902
Max Act: 6.5339. Min Act: -0.1700
Data Index: 2443225 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19