Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1058 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3034. Min Range: -8.3034
Max Act: 8.3034. Min Act: -0.1700
Data Index: 7669091 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.9284. Min Act: -0.1700
Data Index: 3436958 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.9284. Min Act: -0.1700
Data Index: 1400502 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.8659. Min Act: -0.1700
Data Index: 739062 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.8659. Min Act: -0.1700
Data Index: 7026212 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.8659. Min Act: -0.1700
Data Index: 1149799 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.7409. Min Act: -0.1700
Data Index: 6521656 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.6784. Min Act: -0.1700
Data Index: 8050248 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.6784. Min Act: -0.1700
Data Index: 7669090 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.6784. Min Act: -0.1700
Data Index: 5169486 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.6159. Min Act: -0.1700
Data Index: 2429202 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.6159. Min Act: -0.1700
Data Index: 1608776 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.6159. Min Act: -0.1700
Data Index: 6592100 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.6784. Min Act: -0.1700
Data Index: 3998214 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.5534. Min Act: -0.1700
Data Index: 3913061 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.5534. Min Act: -0.1700
Data Index: 4085 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.5534. Min Act: -0.1700
Data Index: 3658608 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.4909. Min Act: -0.1700
Data Index: 1064479 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.4909. Min Act: -0.1700
Data Index: 7838314 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3034. Min Range: -8.3034
Max Act: 7.4909. Min Act: -0.1700
Data Index: 6386787 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19