Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2357 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.9319. Min Act: -0.1700
Data Index: 7624452 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.8381. Min Act: -0.1700
Data Index: 5731458 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.8381. Min Act: -0.1700
Data Index: 8038671 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.8069. Min Act: -0.1700
Data Index: 2647277 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.8069. Min Act: -0.1700
Data Index: 532292 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.7756. Min Act: -0.1700
Data Index: 6977420 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.7756. Min Act: -0.1700
Data Index: 4325591 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.7443. Min Act: -0.1700
Data Index: 3356220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.7443. Min Act: -0.1700
Data Index: 829044 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.7443. Min Act: -0.1700
Data Index: 8363490 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.7443. Min Act: -0.1700
Data Index: 5089339 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.7443. Min Act: -0.1700
Data Index: 1020214 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.7443. Min Act: -0.1700
Data Index: 643029 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.7443. Min Act: -0.1700
Data Index: 8619320 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.7130. Min Act: -0.1700
Data Index: 7459147 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.7130. Min Act: -0.1700
Data Index: 6245478 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.7130. Min Act: -0.1700
Data Index: 7833929 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.7130. Min Act: -0.1700
Data Index: 1071989 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.7130. Min Act: -0.1700
Data Index: 5887736 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9319. Min Range: -3.9319
Max Act: 3.7130. Min Act: -0.1700
Data Index: 3676319 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19