Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3724 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2225. Min Range: -5.2225
Max Act: 5.2225. Min Act: -0.1700
Data Index: 4834637 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2225. Min Range: -5.2225
Max Act: 5.0350. Min Act: -0.1700
Data Index: 2672497 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2225. Min Range: -5.2225
Max Act: 5.0037. Min Act: -0.1700
Data Index: 184468 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2225. Min Range: -5.2225
Max Act: 5.0037. Min Act: -0.1700
Data Index: 4806371 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2225. Min Range: -5.2225
Max Act: 5.0037. Min Act: -0.1700
Data Index: 2765068 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2225. Min Range: -5.2225
Max Act: 4.9725. Min Act: -0.1700
Data Index: 4223239 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2225. Min Range: -5.2225
Max Act: 4.9725. Min Act: -0.1700
Data Index: 2556080 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2225. Min Range: -5.2225
Max Act: 4.9725. Min Act: -0.1700
Data Index: 1396880 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2225. Min Range: -5.2225
Max Act: 4.9100. Min Act: -0.1700
Data Index: 2091931 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2225. Min Range: -5.2225
Max Act: 4.9412. Min Act: -0.1700
Data Index: 6247098 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2225. Min Range: -5.2225
Max Act: 4.9100. Min Act: -0.1700
Data Index: 4687955 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2225. Min Range: -5.2225
Max Act: 4.8787. Min Act: -0.1700
Data Index: 1522453 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2225. Min Range: -5.2225
Max Act: 4.8475. Min Act: -0.1700
Data Index: 6141748 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2225. Min Range: -5.2225
Max Act: 4.8787. Min Act: -0.1700
Data Index: 7801048 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2225. Min Range: -5.2225
Max Act: 4.8787. Min Act: -0.1700
Data Index: 3140683 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2225. Min Range: -5.2225
Max Act: 4.8787. Min Act: -0.1700
Data Index: 1886181 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2225. Min Range: -5.2225
Max Act: 4.8787. Min Act: -0.1700
Data Index: 7249360 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2225. Min Range: -5.2225
Max Act: 4.8475. Min Act: -0.1700
Data Index: 2591569 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2225. Min Range: -5.2225
Max Act: 4.8787. Min Act: -0.1700
Data Index: 2504394 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2225. Min Range: -5.2225
Max Act: 4.8162. Min Act: -0.1700
Data Index: 3327450 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19