Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 526 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.8237. Min Act: -0.1700
Data Index: 5383207 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.8237. Min Act: -0.1700
Data Index: 5638882 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.8237. Min Act: -0.1700
Data Index: 1597715 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.7298. Min Act: -0.1700
Data Index: 5471348 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.7924. Min Act: -0.1700
Data Index: 6985314 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.7924. Min Act: -0.1700
Data Index: 4826175 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.7298. Min Act: -0.1700
Data Index: 4852246 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.7298. Min Act: -0.1700
Data Index: 2979971 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.6985. Min Act: -0.1700
Data Index: 2549192 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.7298. Min Act: -0.1700
Data Index: 8360182 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.6985. Min Act: -0.1700
Data Index: 720609 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.6673. Min Act: -0.1700
Data Index: 1165449 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.6673. Min Act: -0.1700
Data Index: 2959440 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.6673. Min Act: -0.1700
Data Index: 4587250 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.6985. Min Act: -0.1700
Data Index: 4265423 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.6985. Min Act: -0.1700
Data Index: 7895903 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.6673. Min Act: -0.1700
Data Index: 4266235 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.6360. Min Act: -0.1700
Data Index: 6671371 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.6047. Min Act: -0.1700
Data Index: 3411077 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8237. Min Range: -3.8237
Max Act: 3.6360. Min Act: -0.1700
Data Index: 8356446 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19