Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6056 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4834. Min Range: -4.4834
Max Act: 4.4834. Min Act: -0.1700
Data Index: 6493339 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4834. Min Range: -4.4834
Max Act: 4.3896. Min Act: -0.1700
Data Index: 8227584 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.9833. Min Act: -0.1700
Data Index: 1020873 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4834. Min Range: -4.4834
Max Act: 4.0146. Min Act: -0.1700
Data Index: 3091619 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4834. Min Range: -4.4834
Max Act: 4.0458. Min Act: -0.1700
Data Index: 4303158 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.9833. Min Act: -0.1700
Data Index: 2088403 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.9520. Min Act: -0.1700
Data Index: 2168211 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.9520. Min Act: -0.1700
Data Index: 7281026 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.9520. Min Act: -0.1700
Data Index: 1710734 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.9520. Min Act: -0.1700
Data Index: 2122805 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.8895. Min Act: -0.1700
Data Index: 1191982 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.9208. Min Act: -0.1700
Data Index: 3681503 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.9208. Min Act: -0.1700
Data Index: 8337539 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.8895. Min Act: -0.1700
Data Index: 4612684 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.8895. Min Act: -0.1700
Data Index: 5086182 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.8895. Min Act: -0.1700
Data Index: 4352646 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.8582. Min Act: -0.1700
Data Index: 467381 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.8582. Min Act: -0.1700
Data Index: 8145353 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.8270. Min Act: -0.1700
Data Index: 2037005 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4834. Min Range: -4.4834
Max Act: 3.8270. Min Act: -0.1700
Data Index: 5808536 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19