Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1132. Min Range: -4.1132
Max Act: 4.1132. Min Act: -0.1700
Data Index: 1578369 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1132. Min Range: -4.1132
Max Act: 4.0507. Min Act: -0.1700
Data Index: 3991676 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1132. Min Range: -4.1132
Max Act: 4.0507. Min Act: -0.1700
Data Index: 8312225 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1132. Min Range: -4.1132
Max Act: 4.0194. Min Act: -0.1700
Data Index: 890893 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1132. Min Range: -4.1132
Max Act: 4.0194. Min Act: -0.1700
Data Index: 3265200 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1132. Min Range: -4.1132
Max Act: 3.9881. Min Act: -0.1700
Data Index: 6227339 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1132. Min Range: -4.1132
Max Act: 3.9881. Min Act: -0.1700
Data Index: 8638309 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1132. Min Range: -4.1132
Max Act: 3.9881. Min Act: -0.1700
Data Index: 2846381 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1132. Min Range: -4.1132
Max Act: 3.9569. Min Act: -0.1700
Data Index: 3686617 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1132. Min Range: -4.1132
Max Act: 3.9256. Min Act: -0.1700
Data Index: 4771469 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1132. Min Range: -4.1132
Max Act: 3.9256. Min Act: -0.1700
Data Index: 3280501 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1132. Min Range: -4.1132
Max Act: 3.9256. Min Act: -0.1700
Data Index: 2580398 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1132. Min Range: -4.1132
Max Act: 3.9256. Min Act: -0.1700
Data Index: 5534394 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1132. Min Range: -4.1132
Max Act: 3.8944. Min Act: -0.1700
Data Index: 6856623 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1132. Min Range: -4.1132
Max Act: 3.9569. Min Act: -0.1700
Data Index: 145568 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1132. Min Range: -4.1132
Max Act: 3.9256. Min Act: -0.1700
Data Index: 6148798 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1132. Min Range: -4.1132
Max Act: 3.8944. Min Act: -0.1700
Data Index: 5388958 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1132. Min Range: -4.1132
Max Act: 3.8944. Min Act: -0.1700
Data Index: 5768521 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1132. Min Range: -4.1132
Max Act: 3.8944. Min Act: -0.1700
Data Index: 7584412 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1132. Min Range: -4.1132
Max Act: 3.8944. Min Act: -0.1700
Data Index: 5283946 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19