Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4758 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4972. Min Range: -12.4972
Max Act: 12.4972. Min Act: -0.1700
Data Index: 4401170 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4972. Min Range: -12.4972
Max Act: 12.4972. Min Act: -0.1700
Data Index: 6211523 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4972. Min Range: -12.4972
Max Act: 12.2472. Min Act: -0.1700
Data Index: 1672815 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4972. Min Range: -12.4972
Max Act: 12.1847. Min Act: -0.1700
Data Index: 141084 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4972. Min Range: -12.4972
Max Act: 12.2472. Min Act: -0.1700
Data Index: 5662953 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4972. Min Range: -12.4972
Max Act: 12.0597. Min Act: -0.1700
Data Index: 6574303 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4972. Min Range: -12.4972
Max Act: 11.9972. Min Act: -0.1700
Data Index: 465094 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4972. Min Range: -12.4972
Max Act: 11.9972. Min Act: -0.1700
Data Index: 5644041 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4972. Min Range: -12.4972
Max Act: 11.9972. Min Act: -0.1700
Data Index: 2879758 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4972. Min Range: -12.4972
Max Act: 11.9347. Min Act: -0.1700
Data Index: 8247438 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4972. Min Range: -12.4972
Max Act: 11.8722. Min Act: -0.1700
Data Index: 959717 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4972. Min Range: -12.4972
Max Act: 11.8722. Min Act: -0.1700
Data Index: 582376 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4972. Min Range: -12.4972
Max Act: 11.8722. Min Act: -0.1700
Data Index: 5817584 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4972. Min Range: -12.4972
Max Act: 11.8097. Min Act: -0.1700
Data Index: 3083929 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4972. Min Range: -12.4972
Max Act: 11.7472. Min Act: -0.1700
Data Index: 3243506 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4972. Min Range: -12.4972
Max Act: 11.7472. Min Act: -0.1700
Data Index: 5219274 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4972. Min Range: -12.4972
Max Act: 11.6847. Min Act: -0.1700
Data Index: 8768743 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4972. Min Range: -12.4972
Max Act: 11.6847. Min Act: -0.1700
Data Index: 4117781 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4972. Min Range: -12.4972
Max Act: 11.6847. Min Act: -0.1699
Data Index: 3749783 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4972. Min Range: -12.4972
Max Act: 11.6847. Min Act: -0.1700
Data Index: 4623925 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19