Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.2852. Min Act: -0.1700
Data Index: 6727327 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.0977. Min Act: -0.1700
Data Index: 4794053 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.0977. Min Act: -0.1700
Data Index: 1234470 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2852. Min Range: -5.2852
Max Act: 5.0352. Min Act: -0.1700
Data Index: 5191988 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.9415. Min Act: -0.1700
Data Index: 6482772 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.9415. Min Act: -0.1700
Data Index: 1965446 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.8790. Min Act: -0.1700
Data Index: 8764999 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.8790. Min Act: -0.1700
Data Index: 2050009 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.8790. Min Act: -0.1700
Data Index: 7443893 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.8790. Min Act: -0.1700
Data Index: 5264996 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.9102. Min Act: -0.1700
Data Index: 1815711 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.8477. Min Act: -0.1700
Data Index: 2986130 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.8477. Min Act: -0.1700
Data Index: 3302746 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.8477. Min Act: -0.1700
Data Index: 2311645 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.8477. Min Act: -0.1700
Data Index: 8511677 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.8165. Min Act: -0.1700
Data Index: 4294601 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.8165. Min Act: -0.1700
Data Index: 3991400 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.8165. Min Act: -0.1700
Data Index: 1964601 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.8165. Min Act: -0.1700
Data Index: 1283854 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2852. Min Range: -5.2852
Max Act: 4.8165. Min Act: -0.1700
Data Index: 3451952 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19