Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2907 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.8094. Min Act: -0.1700
Data Index: 8462530 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.6844. Min Act: -0.1700
Data Index: 6388890 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.6219. Min Act: -0.1700
Data Index: 1580610 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.5906. Min Act: -0.1700
Data Index: 4471504 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.5906. Min Act: -0.1700
Data Index: 1198873 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.5594. Min Act: -0.1700
Data Index: 3678708 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.5594. Min Act: -0.1700
Data Index: 8187355 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.5281. Min Act: -0.1700
Data Index: 1954553 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.5281. Min Act: -0.1700
Data Index: 724684 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.5281. Min Act: -0.1700
Data Index: 8150189 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.4969. Min Act: -0.1700
Data Index: 1769123 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.4969. Min Act: -0.1700
Data Index: 6656383 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.4656. Min Act: -0.1700
Data Index: 8445381 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.4656. Min Act: -0.1700
Data Index: 5963 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.4344. Min Act: -0.1700
Data Index: 3937825 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.4344. Min Act: -0.1700
Data Index: 2452340 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.4031. Min Act: -0.1700
Data Index: 8548312 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.4344. Min Act: -0.1700
Data Index: 5816912 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.4031. Min Act: -0.1700
Data Index: 5299651 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8094. Min Range: -5.8094
Max Act: 5.4031. Min Act: -0.1700
Data Index: 7342165 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19