Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2416 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4546. Min Range: -8.4546
Max Act: 8.4546. Min Act: -0.1700
Data Index: 7768632 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.7358. Min Act: -0.1700
Data Index: 7910181 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.5483. Min Act: -0.1700
Data Index: 1811671 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.4858. Min Act: -0.1700
Data Index: 392651 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.4858. Min Act: -0.1700
Data Index: 2928463 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.4233. Min Act: -0.1700
Data Index: 4305708 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.2983. Min Act: -0.1700
Data Index: 4697322 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.2983. Min Act: -0.1700
Data Index: 4705609 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.2983. Min Act: -0.1700
Data Index: 4767820 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.2671. Min Act: -0.1700
Data Index: 5329104 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.2358. Min Act: -0.1700
Data Index: 2996622 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.1733. Min Act: -0.1700
Data Index: 7618521 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.2046. Min Act: -0.1700
Data Index: 8155265 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.1733. Min Act: -0.1700
Data Index: 5216467 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.1421. Min Act: -0.1700
Data Index: 5552624 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.1421. Min Act: -0.1700
Data Index: 4844929 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.0483. Min Act: -0.1700
Data Index: 1799548 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.0796. Min Act: -0.1700
Data Index: 6708330 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4546. Min Range: -8.4546
Max Act: 7.0483. Min Act: -0.1700
Data Index: 2964889 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4546. Min Range: -8.4546
Max Act: 6.9858. Min Act: -0.1700
Data Index: 3176817 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19