Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3755 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.9629. Min Act: -0.1700
Data Index: 6244767 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.9004. Min Act: -0.1700
Data Index: 8334284 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.8379. Min Act: -0.1700
Data Index: 3311212 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.8379. Min Act: -0.1700
Data Index: 4648121 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.6504. Min Act: -0.1700
Data Index: 6205798 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.7129. Min Act: -0.1700
Data Index: 4454954 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.6504. Min Act: -0.1700
Data Index: 376077 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.6504. Min Act: -0.1700
Data Index: 5626 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.6504. Min Act: -0.1700
Data Index: 7731027 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.5254. Min Act: -0.1700
Data Index: 2109538 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.5879. Min Act: -0.1700
Data Index: 7019768 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.5254. Min Act: -0.1700
Data Index: 2269655 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.5254. Min Act: -0.1700
Data Index: 3154429 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.5254. Min Act: -0.1700
Data Index: 3461458 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.4629. Min Act: -0.1700
Data Index: 2203317 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.5254. Min Act: -0.1700
Data Index: 3306854 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.4629. Min Act: -0.1700
Data Index: 6400921 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.4629. Min Act: -0.1700
Data Index: 4969228 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.4629. Min Act: -0.1700
Data Index: 923449 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9629. Min Range: -11.9629
Max Act: 11.4629. Min Act: -0.1700
Data Index: 1296708 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19