Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2524 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1164. Min Range: -7.1164
Max Act: 7.1164. Min Act: -0.1700
Data Index: 98211 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1164. Min Range: -7.1164
Max Act: 7.1164. Min Act: -0.1700
Data Index: 4991573 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1164. Min Range: -7.1164
Max Act: 7.0226. Min Act: -0.1700
Data Index: 4661005 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.9914. Min Act: -0.1700
Data Index: 3339429 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1164. Min Range: -7.1164
Max Act: 7.0539. Min Act: -0.1700
Data Index: 3571059 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.9601. Min Act: -0.1700
Data Index: 7095959 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.9601. Min Act: -0.1700
Data Index: 233141 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.9289. Min Act: -0.1700
Data Index: 611641 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.9289. Min Act: -0.1700
Data Index: 3031880 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.8664. Min Act: -0.1700
Data Index: 7734296 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.8664. Min Act: -0.1700
Data Index: 49257 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.8664. Min Act: -0.1700
Data Index: 5520437 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.8664. Min Act: -0.1700
Data Index: 4848143 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.8351. Min Act: -0.1700
Data Index: 4471088 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.8351. Min Act: -0.1700
Data Index: 5168264 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.8351. Min Act: -0.1700
Data Index: 8473583 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.7726. Min Act: -0.1700
Data Index: 8336655 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.8039. Min Act: -0.1700
Data Index: 1229887 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.8039. Min Act: -0.1700
Data Index: 7521536 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1164. Min Range: -7.1164
Max Act: 6.7726. Min Act: -0.1700
Data Index: 3069368 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19