Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6373 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5331. Min Range: -6.5331
Max Act: 6.5331. Min Act: -0.1700
Data Index: 7423807 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5331. Min Range: -6.5331
Max Act: 6.2831. Min Act: -0.1700
Data Index: 7279715 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5331. Min Range: -6.5331
Max Act: 6.2831. Min Act: -0.1700
Data Index: 7899812 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5331. Min Range: -6.5331
Max Act: 6.1269. Min Act: -0.1700
Data Index: 5369259 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5331. Min Range: -6.5331
Max Act: 6.0956. Min Act: -0.1700
Data Index: 4180391 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5331. Min Range: -6.5331
Max Act: 6.0331. Min Act: -0.1700
Data Index: 7725262 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5331. Min Range: -6.5331
Max Act: 6.0019. Min Act: -0.1700
Data Index: 169136 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5331. Min Range: -6.5331
Max Act: 6.0019. Min Act: -0.1700
Data Index: 4239613 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5331. Min Range: -6.5331
Max Act: 6.0019. Min Act: -0.1700
Data Index: 1717564 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5331. Min Range: -6.5331
Max Act: 5.9394. Min Act: -0.1700
Data Index: 3745885 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5331. Min Range: -6.5331
Max Act: 5.8769. Min Act: -0.1700
Data Index: 6819816 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5331. Min Range: -6.5331
Max Act: 5.8769. Min Act: -0.1700
Data Index: 3812107 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5331. Min Range: -6.5331
Max Act: 5.8769. Min Act: -0.1700
Data Index: 902002 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5331. Min Range: -6.5331
Max Act: 5.8769. Min Act: -0.1700
Data Index: 2869653 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5331. Min Range: -6.5331
Max Act: 5.8456. Min Act: -0.1700
Data Index: 7158502 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5331. Min Range: -6.5331
Max Act: 5.8769. Min Act: -0.1700
Data Index: 5104879 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5331. Min Range: -6.5331
Max Act: 5.8456. Min Act: -0.1700
Data Index: 6337479 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5331. Min Range: -6.5331
Max Act: 5.8456. Min Act: -0.1700
Data Index: 4011087 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5331. Min Range: -6.5331
Max Act: 5.8144. Min Act: -0.1700
Data Index: 3210194 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5331. Min Range: -6.5331
Max Act: 5.7831. Min Act: -0.1700
Data Index: 427028 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19