Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1540 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.8366. Min Act: -0.1700
Data Index: 3132211 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.5241. Min Act: -0.1700
Data Index: 8489357 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.4928. Min Act: -0.1700
Data Index: 6393088 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.3991. Min Act: -0.1700
Data Index: 4485983 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.3991. Min Act: -0.1700
Data Index: 5141871 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.3366. Min Act: -0.1700
Data Index: 6379386 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.3053. Min Act: -0.1700
Data Index: 4896297 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.2116. Min Act: -0.1700
Data Index: 6138815 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.1491. Min Act: -0.1700
Data Index: 1192967 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.1491. Min Act: -0.1700
Data Index: 5083583 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.1491. Min Act: -0.1700
Data Index: 5934704 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.0866. Min Act: -0.1700
Data Index: 7202990 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.0866. Min Act: -0.1700
Data Index: 443831 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.0553. Min Act: -0.1700
Data Index: 5351486 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.0553. Min Act: -0.1700
Data Index: 4672704 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.0553. Min Act: -0.1700
Data Index: 5859903 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.0241. Min Act: -0.1700
Data Index: 1804598 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.0241. Min Act: -0.1700
Data Index: 2211327 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.0241. Min Act: -0.1700
Data Index: 6249752 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8366. Min Range: -7.8366
Max Act: 7.0241. Min Act: -0.1700
Data Index: 3655441 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19