Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1046 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.3736. Min Act: -0.1700
Data Index: 645513 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.2486. Min Act: -0.1700
Data Index: 2864048 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.2174. Min Act: -0.1700
Data Index: 6709906 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.1549. Min Act: -0.1700
Data Index: 4571995 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.0924. Min Act: -0.1700
Data Index: 2477683 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.1236. Min Act: -0.1700
Data Index: 8410713 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.1236. Min Act: -0.1700
Data Index: 8650001 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.0924. Min Act: -0.1700
Data Index: 442597 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.0924. Min Act: -0.1700
Data Index: 26166 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.0611. Min Act: -0.1700
Data Index: 312005 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.0611. Min Act: -0.1700
Data Index: 5908902 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.0611. Min Act: -0.1700
Data Index: 8619207 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9986. Min Act: -0.1700
Data Index: 1804194 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9986. Min Act: -0.1700
Data Index: 5821639 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9674. Min Act: -0.1700
Data Index: 7311280 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9986. Min Act: -0.1700
Data Index: 8278080 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9674. Min Act: -0.1700
Data Index: 3928389 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9674. Min Act: -0.1700
Data Index: 530637 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9674. Min Act: -0.1700
Data Index: 8250234 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9674. Min Act: -0.1700
Data Index: 8448518 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19