Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 930 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.8537. Min Act: -0.1700
Data Index: 1441121 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.8225. Min Act: -0.1700
Data Index: 6434597 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.7600. Min Act: -0.1700
Data Index: 8509738 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.7912. Min Act: -0.1700
Data Index: 7874565 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.7912. Min Act: -0.1700
Data Index: 7880707 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.7287. Min Act: -0.1700
Data Index: 5055555 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.6975. Min Act: -0.1700
Data Index: 4691478 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.6662. Min Act: -0.1700
Data Index: 4103617 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.6662. Min Act: -0.1700
Data Index: 1466184 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.6662. Min Act: -0.1700
Data Index: 1819962 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.6662. Min Act: -0.1700
Data Index: 3996097 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.6350. Min Act: -0.1700
Data Index: 2027083 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.6350. Min Act: -0.1700
Data Index: 6723796 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.6662. Min Act: -0.1700
Data Index: 6807330 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.6037. Min Act: -0.1700
Data Index: 6679697 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.6037. Min Act: -0.1700
Data Index: 2527068 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.5725. Min Act: -0.1700
Data Index: 7796967 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.5100. Min Act: -0.1700
Data Index: 2305309 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.5100. Min Act: -0.1700
Data Index: 7095505 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8537. Min Range: -5.8537
Max Act: 5.4787. Min Act: -0.1700
Data Index: 1400225 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19