Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0710. Min Range: -5.0710
Max Act: 5.0710. Min Act: -0.1700
Data Index: 6826875 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0710. Min Range: -5.0710
Max Act: 5.0085. Min Act: -0.1700
Data Index: 4213807 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0710. Min Range: -5.0710
Max Act: 5.0085. Min Act: -0.1700
Data Index: 3630048 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0710. Min Range: -5.0710
Max Act: 5.0085. Min Act: -0.1700
Data Index: 2865873 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.9460. Min Act: -0.1700
Data Index: 6815897 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.8835. Min Act: -0.1700
Data Index: 5941096 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.8522. Min Act: -0.1700
Data Index: 3039088 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.8522. Min Act: -0.1700
Data Index: 7972232 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.8210. Min Act: -0.1700
Data Index: 7016165 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.7897. Min Act: -0.1700
Data Index: 3715912 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.7897. Min Act: -0.1700
Data Index: 3816226 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.7897. Min Act: -0.1700
Data Index: 8194192 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.7897. Min Act: -0.1700
Data Index: 3039089 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.7585. Min Act: -0.1700
Data Index: 5551781 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.7585. Min Act: -0.1700
Data Index: 3388683 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.7585. Min Act: -0.1700
Data Index: 3039086 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.7585. Min Act: -0.1700
Data Index: 3039084 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.7585. Min Act: -0.1700
Data Index: 7110668 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.7585. Min Act: -0.1700
Data Index: 5708321 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0710. Min Range: -5.0710
Max Act: 4.7897. Min Act: -0.1700
Data Index: 4355385 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19