Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1984 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.6819. Min Act: -0.1700
Data Index: 3116138 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.4319. Min Act: -0.1700
Data Index: 2325568 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.3382. Min Act: -0.1700
Data Index: 4008334 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.3382. Min Act: -0.1700
Data Index: 7042240 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.3069. Min Act: -0.1700
Data Index: 8657720 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.3069. Min Act: -0.1700
Data Index: 8304717 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.2757. Min Act: -0.1700
Data Index: 2619952 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.2132. Min Act: -0.1700
Data Index: 2205750 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.2132. Min Act: -0.1700
Data Index: 7553764 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.2132. Min Act: -0.1700
Data Index: 874028 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.1819. Min Act: -0.1700
Data Index: 4084197 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.1819. Min Act: -0.1700
Data Index: 1433633 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.1194. Min Act: -0.1700
Data Index: 6760183 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.1507. Min Act: -0.1700
Data Index: 398026 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.1194. Min Act: -0.1700
Data Index: 4656338 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.1194. Min Act: -0.1700
Data Index: 5474290 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.0569. Min Act: -0.1700
Data Index: 583197 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.0882. Min Act: -0.1700
Data Index: 2934326 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.0882. Min Act: -0.1700
Data Index: 6519237 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6819. Min Range: -6.6819
Max Act: 6.0569. Min Act: -0.1700
Data Index: 5641532 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19