Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3312 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.8126. Min Act: -0.1700
Data Index: 7066823 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.6563. Min Act: -0.1700
Data Index: 8444461 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.5626. Min Act: -0.1700
Data Index: 4502561 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.5001. Min Act: -0.1700
Data Index: 2920314 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.5313. Min Act: -0.1700
Data Index: 2604081 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.5001. Min Act: -0.1700
Data Index: 5505458 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.5001. Min Act: -0.1700
Data Index: 4672384 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.4376. Min Act: -0.1700
Data Index: 1433442 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.4063. Min Act: -0.1700
Data Index: 8168400 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.3751. Min Act: -0.1700
Data Index: 7712350 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.3438. Min Act: -0.1700
Data Index: 8323187 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.3438. Min Act: -0.1700
Data Index: 7191651 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.3438. Min Act: -0.1700
Data Index: 1524877 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.2813. Min Act: -0.1700
Data Index: 7263059 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.3438. Min Act: -0.1700
Data Index: 6354107 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.3126. Min Act: -0.1700
Data Index: 5436853 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.2813. Min Act: -0.1700
Data Index: 7480244 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.2813. Min Act: -0.1700
Data Index: 5968662 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.2813. Min Act: -0.1700
Data Index: 502893 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8126. Min Range: -5.8126
Max Act: 5.2501. Min Act: -0.1700
Data Index: 1672580 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19