Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3678 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.9524. Min Act: -0.1700
Data Index: 4201949 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.8273. Min Act: -0.1700
Data Index: 4081832 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.7648. Min Act: -0.1700
Data Index: 2570727 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.7022. Min Act: -0.1700
Data Index: 356970 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.7022. Min Act: -0.1700
Data Index: 7408684 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.6709. Min Act: -0.1700
Data Index: 8674701 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.6709. Min Act: -0.1700
Data Index: 2307311 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.6397. Min Act: -0.1700
Data Index: 2509872 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.6397. Min Act: -0.1700
Data Index: 1111824 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.6397. Min Act: -0.1700
Data Index: 3871410 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.6397. Min Act: -0.1700
Data Index: 1001203 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.6397. Min Act: -0.1700
Data Index: 5274147 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.6084. Min Act: -0.1700
Data Index: 7192976 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.6084. Min Act: -0.1700
Data Index: 3321051 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.6084. Min Act: -0.1700
Data Index: 7048015 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.6084. Min Act: -0.1700
Data Index: 7494956 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.6084. Min Act: -0.1700
Data Index: 1680879 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.6084. Min Act: -0.1700
Data Index: 4143205 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.5771. Min Act: -0.1700
Data Index: 39779 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9524. Min Range: -3.9524
Max Act: 3.5771. Min Act: -0.1700
Data Index: 1139708 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19