Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 451 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2952. Min Range: -5.2952
Max Act: 5.2952. Min Act: -0.1700
Data Index: 6079429 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2952. Min Range: -5.2952
Max Act: 5.2640. Min Act: -0.1700
Data Index: 6155204 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2952. Min Range: -5.2952
Max Act: 5.1702. Min Act: -0.1700
Data Index: 2518201 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2952. Min Range: -5.2952
Max Act: 5.0765. Min Act: -0.1700
Data Index: 2914668 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2952. Min Range: -5.2952
Max Act: 5.0765. Min Act: -0.1700
Data Index: 7818899 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2952. Min Range: -5.2952
Max Act: 5.0452. Min Act: -0.1700
Data Index: 2914659 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2952. Min Range: -5.2952
Max Act: 5.0140. Min Act: -0.1700
Data Index: 2158416 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.9827. Min Act: -0.1700
Data Index: 1487572 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.9827. Min Act: -0.1700
Data Index: 8518178 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.9515. Min Act: -0.1700
Data Index: 8275324 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.9515. Min Act: -0.1700
Data Index: 6489349 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.9515. Min Act: -0.1700
Data Index: 4722105 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.9515. Min Act: -0.1700
Data Index: 2925648 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.9202. Min Act: -0.1700
Data Index: 8060264 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.9202. Min Act: -0.1700
Data Index: 2974097 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.9202. Min Act: -0.1700
Data Index: 4673692 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.9202. Min Act: -0.1700
Data Index: 933045 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.9202. Min Act: -0.1700
Data Index: 2925669 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.9202. Min Act: -0.1700
Data Index: 2925694 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2952. Min Range: -5.2952
Max Act: 4.9202. Min Act: -0.1700
Data Index: 918906 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19