Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2608 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.9456. Min Act: -0.1700
Data Index: 2237413 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.9456. Min Act: -0.1700
Data Index: 7064974 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.8206. Min Act: -0.1700
Data Index: 7555233 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.7893. Min Act: -0.1699
Data Index: 4963289 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.7581. Min Act: -0.1700
Data Index: 6226753 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.7268. Min Act: -0.1700
Data Index: 7555234 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6956. Min Act: -0.1700
Data Index: 277087 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6956. Min Act: -0.1700
Data Index: 5394855 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6643. Min Act: -0.1700
Data Index: 1019783 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6643. Min Act: -0.1700
Data Index: 5622973 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6643. Min Act: -0.1700
Data Index: 3802454 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6643. Min Act: -0.1700
Data Index: 2136145 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6643. Min Act: -0.1700
Data Index: 2600677 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6643. Min Act: -0.1700
Data Index: 6675187 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6643. Min Act: -0.1700
Data Index: 1105840 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6643. Min Act: -0.1700
Data Index: 6700108 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6643. Min Act: -0.1700
Data Index: 2237415 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6331. Min Act: -0.1700
Data Index: 8713625 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6331. Min Act: -0.1700
Data Index: 7628879 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6331. Min Act: -0.1700
Data Index: 6764307 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19