Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3134 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.4710. Min Act: -0.1700
Data Index: 2344817 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.4397. Min Act: -0.1700
Data Index: 1537270 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.3147. Min Act: -0.1700
Data Index: 2363347 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.3459. Min Act: -0.1700
Data Index: 6525462 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.3147. Min Act: -0.1700
Data Index: 5836308 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.2522. Min Act: -0.1700
Data Index: 5740401 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.2209. Min Act: -0.1700
Data Index: 3676869 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.2522. Min Act: -0.1700
Data Index: 7580279 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.2522. Min Act: -0.1700
Data Index: 5183380 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.2522. Min Act: -0.1700
Data Index: 810494 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.2209. Min Act: -0.1700
Data Index: 7057620 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.2209. Min Act: -0.1700
Data Index: 6671758 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.1897. Min Act: -0.1700
Data Index: 8199100 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.1584. Min Act: -0.1700
Data Index: 956197 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.1897. Min Act: -0.1700
Data Index: 5542518 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.1897. Min Act: -0.1700
Data Index: 38054 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.1897. Min Act: -0.1700
Data Index: 8420257 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.1584. Min Act: -0.1700
Data Index: 2575945 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.1584. Min Act: -0.1700
Data Index: 2536946 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4710. Min Range: -4.4710
Max Act: 4.1584. Min Act: -0.1700
Data Index: 7139668 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19