Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3779 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.9085. Min Act: -0.1700
Data Index: 293873 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.9085. Min Act: -0.1700
Data Index: 4519930 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.9085. Min Act: -0.1700
Data Index: 1388072 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.9085. Min Act: -0.1700
Data Index: 805509 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.9085. Min Act: -0.1700
Data Index: 2238404 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.9085. Min Act: -0.1700
Data Index: 2581488 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8773. Min Act: -0.1700
Data Index: 4422595 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8773. Min Act: -0.1700
Data Index: 4883553 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8773. Min Act: -0.1700
Data Index: 5110284 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8773. Min Act: -0.1700
Data Index: 286388 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8147. Min Act: -0.1700
Data Index: 6769084 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8460. Min Act: -0.1700
Data Index: 4222872 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8147. Min Act: -0.1700
Data Index: 3892244 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8460. Min Act: -0.1700
Data Index: 1727922 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8460. Min Act: -0.1700
Data Index: 4699100 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8147. Min Act: -0.1700
Data Index: 467639 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8147. Min Act: -0.1700
Data Index: 499019 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8147. Min Act: -0.1700
Data Index: 1838081 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8147. Min Act: -0.1700
Data Index: 3985247 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9085. Min Range: -3.9085
Max Act: 3.8147. Min Act: -0.1700
Data Index: 2889627 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19