Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3205 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1852. Min Range: -5.1852
Max Act: 5.1852. Min Act: -0.1700
Data Index: 6074320 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1852. Min Range: -5.1852
Max Act: 5.1852. Min Act: -0.1700
Data Index: 1980694 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1852. Min Range: -5.1852
Max Act: 5.0602. Min Act: -0.1700
Data Index: 3976499 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1852. Min Range: -5.1852
Max Act: 5.0602. Min Act: -0.1700
Data Index: 2449850 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1852. Min Range: -5.1852
Max Act: 5.0915. Min Act: -0.1700
Data Index: 3853806 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1852. Min Range: -5.1852
Max Act: 5.0602. Min Act: -0.1700
Data Index: 4546574 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1852. Min Range: -5.1852
Max Act: 5.0290. Min Act: -0.1700
Data Index: 5304162 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1852. Min Range: -5.1852
Max Act: 4.9977. Min Act: -0.1700
Data Index: 5574531 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1852. Min Range: -5.1852
Max Act: 4.9977. Min Act: -0.1700
Data Index: 743723 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1852. Min Range: -5.1852
Max Act: 4.9665. Min Act: -0.1700
Data Index: 6614864 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1852. Min Range: -5.1852
Max Act: 4.9665. Min Act: -0.1700
Data Index: 4515633 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1852. Min Range: -5.1852
Max Act: 4.9665. Min Act: -0.1700
Data Index: 2044529 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1852. Min Range: -5.1852
Max Act: 4.9665. Min Act: -0.1700
Data Index: 8207960 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1852. Min Range: -5.1852
Max Act: 4.9665. Min Act: -0.1700
Data Index: 1298046 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1852. Min Range: -5.1852
Max Act: 4.9352. Min Act: -0.1700
Data Index: 6824591 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1852. Min Range: -5.1852
Max Act: 4.9352. Min Act: -0.1700
Data Index: 6161969 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1852. Min Range: -5.1852
Max Act: 4.9352. Min Act: -0.1700
Data Index: 2435860 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1852. Min Range: -5.1852
Max Act: 4.9665. Min Act: -0.1700
Data Index: 2384121 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1852. Min Range: -5.1852
Max Act: 4.9040. Min Act: -0.1700
Data Index: 3680758 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1852. Min Range: -5.1852
Max Act: 4.9040. Min Act: -0.1700
Data Index: 8094985 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19