Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4485 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9266. Min Range: -5.9266
Max Act: 5.9266. Min Act: -0.1700
Data Index: 6849347 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9266. Min Range: -5.9266
Max Act: 5.3016. Min Act: -0.1700
Data Index: 7914488 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9266. Min Range: -5.9266
Max Act: 5.2703. Min Act: -0.1700
Data Index: 2740526 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9266. Min Range: -5.9266
Max Act: 5.1766. Min Act: -0.1700
Data Index: 6802513 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9266. Min Range: -5.9266
Max Act: 5.1453. Min Act: -0.1700
Data Index: 2653134 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9266. Min Range: -5.9266
Max Act: 5.1453. Min Act: -0.1700
Data Index: 4152452 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9266. Min Range: -5.9266
Max Act: 5.0828. Min Act: -0.1700
Data Index: 12531 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9266. Min Range: -5.9266
Max Act: 5.0516. Min Act: -0.1700
Data Index: 7021314 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9266. Min Range: -5.9266
Max Act: 5.0516. Min Act: -0.1700
Data Index: 3414789 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9266. Min Range: -5.9266
Max Act: 5.0516. Min Act: -0.1700
Data Index: 759925 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9266. Min Range: -5.9266
Max Act: 5.0203. Min Act: -0.1700
Data Index: 3899809 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9266. Min Range: -5.9266
Max Act: 5.0203. Min Act: -0.1700
Data Index: 1878871 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9266. Min Range: -5.9266
Max Act: 5.0516. Min Act: -0.1700
Data Index: 2390573 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9266. Min Range: -5.9266
Max Act: 5.0203. Min Act: -0.1700
Data Index: 6104048 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9266. Min Range: -5.9266
Max Act: 4.9891. Min Act: -0.1700
Data Index: 6733729 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9266. Min Range: -5.9266
Max Act: 4.9578. Min Act: -0.1700
Data Index: 7882286 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9266. Min Range: -5.9266
Max Act: 4.9266. Min Act: -0.1700
Data Index: 167166 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9266. Min Range: -5.9266
Max Act: 4.9266. Min Act: -0.1700
Data Index: 1811366 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9266. Min Range: -5.9266
Max Act: 4.9266. Min Act: -0.1700
Data Index: 6342322 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9266. Min Range: -5.9266
Max Act: 4.8953. Min Act: -0.1700
Data Index: 5065311 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19