Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 328 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.8365. Min Act: -0.1700
Data Index: 2984600 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.7740. Min Act: -0.1700
Data Index: 7755873 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.7740. Min Act: -0.1700
Data Index: 3030051 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.7115. Min Act: -0.1700
Data Index: 4191662 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.7115. Min Act: -0.1700
Data Index: 4882668 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.7115. Min Act: -0.1700
Data Index: 7310596 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.6490. Min Act: -0.1700
Data Index: 2892903 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.5240. Min Act: -0.1700
Data Index: 4285320 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.5240. Min Act: -0.1700
Data Index: 3559611 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.5240. Min Act: -0.1700
Data Index: 31078 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.4615. Min Act: -0.1700
Data Index: 5167677 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.5240. Min Act: -0.1700
Data Index: 3645643 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.4615. Min Act: -0.1700
Data Index: 6915780 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.3990. Min Act: -0.1700
Data Index: 6315225 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.3365. Min Act: -0.1700
Data Index: 7310601 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.3365. Min Act: -0.1700
Data Index: 7166512 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.2740. Min Act: -0.1700
Data Index: 172618 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.2740. Min Act: -0.1700
Data Index: 831258 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.2740. Min Act: -0.1700
Data Index: 6342504 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8365. Min Range: -8.8365
Max Act: 8.2115. Min Act: -0.1700
Data Index: 2671168 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19