Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2872 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.5367. Min Act: -0.1700
Data Index: 8556707 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.4742. Min Act: -0.1700
Data Index: 2714469 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.4742. Min Act: -0.1700
Data Index: 3676852 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.4117. Min Act: -0.1700
Data Index: 8170037 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.4117. Min Act: -0.1700
Data Index: 8094845 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.3492. Min Act: -0.1700
Data Index: 92875 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.4117. Min Act: -0.1700
Data Index: 235843 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.3492. Min Act: -0.1700
Data Index: 32118 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.2867. Min Act: -0.1700
Data Index: 6388579 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.2867. Min Act: -0.1700
Data Index: 1456509 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.2867. Min Act: -0.1700
Data Index: 50440 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.2867. Min Act: -0.1700
Data Index: 7863416 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.2867. Min Act: -0.1700
Data Index: 3694601 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.2867. Min Act: -0.1700
Data Index: 1094670 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.2867. Min Act: -0.1700
Data Index: 3130362 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.2867. Min Act: -0.1700
Data Index: 745292 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.2867. Min Act: -0.1700
Data Index: 4156261 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.2867. Min Act: -0.1700
Data Index: 4228618 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.2242. Min Act: -0.1700
Data Index: 891994 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5367. Min Range: -8.5367
Max Act: 8.2242. Min Act: -0.1700
Data Index: 2712214 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19