Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3620 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.4847. Min Act: -0.1700
Data Index: 2296527 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.1722. Min Act: -0.1700
Data Index: 2534118 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.1722. Min Act: -0.1700
Data Index: 6104533 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.1097. Min Act: -0.1700
Data Index: 7940231 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.0784. Min Act: -0.1700
Data Index: 8640772 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.0472. Min Act: -0.1700
Data Index: 3531314 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.1097. Min Act: -0.1700
Data Index: 5733338 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.0784. Min Act: -0.1700
Data Index: 7929241 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.0472. Min Act: -0.1700
Data Index: 813078 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.0159. Min Act: -0.1700
Data Index: 279639 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.0472. Min Act: -0.1700
Data Index: 1388855 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.0472. Min Act: -0.1700
Data Index: 7955591 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.0159. Min Act: -0.1700
Data Index: 4444637 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.0159. Min Act: -0.1700
Data Index: 1485784 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.0159. Min Act: -0.1700
Data Index: 7870041 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.0159. Min Act: -0.1700
Data Index: 8633408 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4847. Min Range: -4.4847
Max Act: 4.0159. Min Act: -0.1700
Data Index: 2124158 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4847. Min Range: -4.4847
Max Act: 3.9534. Min Act: -0.1700
Data Index: 3567653 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4847. Min Range: -4.4847
Max Act: 3.9534. Min Act: -0.1700
Data Index: 2103674 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4847. Min Range: -4.4847
Max Act: 3.9534. Min Act: -0.1700
Data Index: 2609732 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19