Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1351 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.6353. Min Act: -0.1700
Data Index: 1405281 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.6353. Min Act: -0.1700
Data Index: 4485537 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.6041. Min Act: -0.1700
Data Index: 4287063 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.5728. Min Act: -0.1700
Data Index: 8237181 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.5728. Min Act: -0.1700
Data Index: 650000 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.5416. Min Act: -0.1700
Data Index: 673212 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.5416. Min Act: -0.1700
Data Index: 98537 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.5416. Min Act: -0.1700
Data Index: 538555 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.5416. Min Act: -0.1700
Data Index: 3657600 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.4791. Min Act: -0.1700
Data Index: 630834 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.5103. Min Act: -0.1700
Data Index: 6568629 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.4791. Min Act: -0.1700
Data Index: 814979 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.4478. Min Act: -0.1700
Data Index: 2579704 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.4166. Min Act: -0.1700
Data Index: 849418 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.4166. Min Act: -0.1700
Data Index: 2147153 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.4166. Min Act: -0.1700
Data Index: 5289545 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.3853. Min Act: -0.1700
Data Index: 8202221 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.3853. Min Act: -0.1700
Data Index: 3415804 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.3853. Min Act: -0.1700
Data Index: 401548 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.3541. Min Act: -0.1700
Data Index: 670554 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19