Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4244 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0031. Min Range: -6.0031
Max Act: 6.0031. Min Act: -0.1700
Data Index: 4524470 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.8781. Min Act: -0.1700
Data Index: 2561245 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.8156. Min Act: -0.1700
Data Index: 3857284 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.7844. Min Act: -0.1700
Data Index: 8805018 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.7219. Min Act: -0.1700
Data Index: 7293371 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.6906. Min Act: -0.1700
Data Index: 370883 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.6906. Min Act: -0.1700
Data Index: 6836012 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.6281. Min Act: -0.1700
Data Index: 5581634 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.6594. Min Act: -0.1700
Data Index: 6203123 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.5969. Min Act: -0.1700
Data Index: 2262918 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.5969. Min Act: -0.1700
Data Index: 2891040 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.5656. Min Act: -0.1700
Data Index: 6771452 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.5656. Min Act: -0.1700
Data Index: 3289164 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.5656. Min Act: -0.1700
Data Index: 5276628 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.5031. Min Act: -0.1700
Data Index: 7554764 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.5344. Min Act: -0.1700
Data Index: 8417787 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.5344. Min Act: -0.1700
Data Index: 6330429 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.5344. Min Act: -0.1700
Data Index: 6415965 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.5031. Min Act: -0.1700
Data Index: 5594044 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0031. Min Range: -6.0031
Max Act: 5.5031. Min Act: -0.1700
Data Index: 5918974 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19