Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.5515. Min Act: -0.1700
Data Index: 979694 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.3321. Min Act: -0.1700
Data Index: 7541095 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.2221. Min Act: -0.1700
Data Index: 7875476 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.1907. Min Act: -0.1700
Data Index: 964852 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.1750. Min Act: -0.1700
Data Index: 6361989 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.1435. Min Act: -0.1700
Data Index: 4502723 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.0962. Min Act: -0.1700
Data Index: 520649 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.0962. Min Act: -0.1700
Data Index: 2270245 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.0805. Min Act: -0.1700
Data Index: 432060 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.0805. Min Act: -0.1700
Data Index: 3627877 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.0805. Min Act: -0.1700
Data Index: 4957256 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.0489. Min Act: -0.1700
Data Index: 4090511 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.0331. Min Act: -0.1700
Data Index: 7053278 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.0489. Min Act: -0.1700
Data Index: 7472763 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.0331. Min Act: -0.1700
Data Index: 7604171 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.0173. Min Act: -0.1700
Data Index: 5141179 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.0015. Min Act: -0.1700
Data Index: 8465196 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.0015. Min Act: -0.1700
Data Index: 2026430 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5515. Min Range: -3.5515
Max Act: 3.0015. Min Act: -0.1700
Data Index: 4738356 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5515. Min Range: -3.5515
Max Act: 2.9857. Min Act: -0.1700
Data Index: 1377647 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19