Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3762 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1366. Min Range: -4.1366
Max Act: 4.1366. Min Act: -0.1700
Data Index: 5699454 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1366. Min Range: -4.1366
Max Act: 4.1054. Min Act: -0.1700
Data Index: 5337870 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1366. Min Range: -4.1366
Max Act: 4.0429. Min Act: -0.1700
Data Index: 7708890 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1366. Min Range: -4.1366
Max Act: 4.0429. Min Act: -0.1700
Data Index: 6242585 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1366. Min Range: -4.1366
Max Act: 4.0116. Min Act: -0.1700
Data Index: 3876569 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1366. Min Range: -4.1366
Max Act: 4.0116. Min Act: -0.1700
Data Index: 1808664 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1366. Min Range: -4.1366
Max Act: 3.9803. Min Act: -0.1700
Data Index: 1842287 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1366. Min Range: -4.1366
Max Act: 3.9803. Min Act: -0.1700
Data Index: 5100159 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1366. Min Range: -4.1366
Max Act: 3.9803. Min Act: -0.1700
Data Index: 8187571 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1366. Min Range: -4.1366
Max Act: 3.9803. Min Act: -0.1700
Data Index: 3218854 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1366. Min Range: -4.1366
Max Act: 3.9491. Min Act: -0.1700
Data Index: 2243652 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1366. Min Range: -4.1366
Max Act: 3.9491. Min Act: -0.1700
Data Index: 4249388 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1366. Min Range: -4.1366
Max Act: 3.9178. Min Act: -0.1700
Data Index: 5007779 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1366. Min Range: -4.1366
Max Act: 3.9178. Min Act: -0.1700
Data Index: 4748252 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1366. Min Range: -4.1366
Max Act: 3.9491. Min Act: -0.1700
Data Index: 268482 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1366. Min Range: -4.1366
Max Act: 3.9491. Min Act: -0.1700
Data Index: 1379980 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1366. Min Range: -4.1366
Max Act: 3.9491. Min Act: -0.1700
Data Index: 101035 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1366. Min Range: -4.1366
Max Act: 3.9178. Min Act: -0.1700
Data Index: 3073610 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1366. Min Range: -4.1366
Max Act: 3.9491. Min Act: -0.1700
Data Index: 1062589 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1366. Min Range: -4.1366
Max Act: 3.8866. Min Act: -0.1700
Data Index: 4334135 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19