Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1919 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.4225. Min Act: -0.1700
Data Index: 5145444 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.4225. Min Act: -0.1700
Data Index: 7970000 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.4225. Min Act: -0.1700
Data Index: 2853550 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.4225. Min Act: -0.1700
Data Index: 3585761 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.3600. Min Act: -0.1700
Data Index: 1149836 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.3600. Min Act: -0.1700
Data Index: 2039279 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.3600. Min Act: -0.1700
Data Index: 3714666 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.3600. Min Act: -0.1700
Data Index: 2468525 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.3600. Min Act: -0.1700
Data Index: 4115427 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.3600. Min Act: -0.1700
Data Index: 5811299 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.2350. Min Act: -0.1700
Data Index: 708344 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.2662. Min Act: -0.1700
Data Index: 5852209 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.2662. Min Act: -0.1700
Data Index: 934859 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.2662. Min Act: -0.1700
Data Index: 7017225 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.2350. Min Act: -0.1700
Data Index: 2709510 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.1725. Min Act: -0.1700
Data Index: 142498 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.1725. Min Act: -0.1700
Data Index: 4050103 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.1725. Min Act: -0.1700
Data Index: 6847594 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.1725. Min Act: -0.1700
Data Index: 3469961 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4225. Min Range: -4.4225
Max Act: 4.1725. Min Act: -0.1700
Data Index: 1041086 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19