Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4936 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0406. Min Range: -8.0406
Max Act: 8.0406. Min Act: -0.1700
Data Index: 2546563 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.9156. Min Act: -0.1700
Data Index: 1675827 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.7906. Min Act: -0.1700
Data Index: 1379420 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.6656. Min Act: -0.1700
Data Index: 2321153 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.6656. Min Act: -0.1700
Data Index: 5669731 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.6031. Min Act: -0.1700
Data Index: 28509 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.5406. Min Act: -0.1700
Data Index: 6780902 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.5406. Min Act: -0.1700
Data Index: 710761 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.5406. Min Act: -0.1700
Data Index: 4049962 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.5094. Min Act: -0.1700
Data Index: 2058287 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.4781. Min Act: -0.1700
Data Index: 2901238 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.4469. Min Act: -0.1700
Data Index: 111144 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.4156. Min Act: -0.1700
Data Index: 2178674 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.3531. Min Act: -0.1700
Data Index: 8015709 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.3531. Min Act: -0.1700
Data Index: 562908 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.3219. Min Act: -0.1700
Data Index: 4259714 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.3219. Min Act: -0.1700
Data Index: 8499786 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.3219. Min Act: -0.1700
Data Index: 8142697 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.3531. Min Act: -0.1700
Data Index: 5637591 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0406. Min Range: -8.0406
Max Act: 7.2906. Min Act: -0.1700
Data Index: 7460581 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19