Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4046 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0202. Min Range: -6.0202
Max Act: 6.0202. Min Act: -0.1700
Data Index: 2760409 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0202. Min Range: -6.0202
Max Act: 6.0202. Min Act: -0.1700
Data Index: 8247389 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.9890. Min Act: -0.1700
Data Index: 8536148 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.9265. Min Act: -0.1700
Data Index: 290950 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.8640. Min Act: -0.1700
Data Index: 2258150 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.8640. Min Act: -0.1700
Data Index: 6631319 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.8327. Min Act: -0.1700
Data Index: 2163692 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.8327. Min Act: -0.1700
Data Index: 3510854 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.8327. Min Act: -0.1700
Data Index: 7154250 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.8015. Min Act: -0.1700
Data Index: 6060507 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.8015. Min Act: -0.1700
Data Index: 121927 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.7702. Min Act: -0.1700
Data Index: 2584438 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.7702. Min Act: -0.1700
Data Index: 5568130 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.7390. Min Act: -0.1700
Data Index: 7575640 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.7077. Min Act: -0.1700
Data Index: 4758911 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.7390. Min Act: -0.1700
Data Index: 4710568 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.7077. Min Act: -0.1700
Data Index: 6116414 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.7390. Min Act: -0.1700
Data Index: 6745534 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.7390. Min Act: -0.1700
Data Index: 6573849 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0202. Min Range: -6.0202
Max Act: 5.7077. Min Act: -0.1700
Data Index: 6593385 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19