Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3565. Min Range: -6.3565
Max Act: 6.3565. Min Act: -0.1700
Data Index: 7987389 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3565. Min Range: -6.3565
Max Act: 6.1690. Min Act: -0.1700
Data Index: 5865774 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3565. Min Range: -6.3565
Max Act: 6.1690. Min Act: -0.1700
Data Index: 8459625 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3565. Min Range: -6.3565
Max Act: 6.1065. Min Act: -0.1700
Data Index: 8547996 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3565. Min Range: -6.3565
Max Act: 6.0440. Min Act: -0.1700
Data Index: 7989118 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3565. Min Range: -6.3565
Max Act: 6.0127. Min Act: -0.1700
Data Index: 6822749 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3565. Min Range: -6.3565
Max Act: 5.9815. Min Act: -0.1700
Data Index: 2159889 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3565. Min Range: -6.3565
Max Act: 5.9815. Min Act: -0.1700
Data Index: 3542732 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3565. Min Range: -6.3565
Max Act: 5.9815. Min Act: -0.1700
Data Index: 4703052 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3565. Min Range: -6.3565
Max Act: 5.9502. Min Act: -0.1700
Data Index: 6921620 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3565. Min Range: -6.3565
Max Act: 5.9815. Min Act: -0.1700
Data Index: 1737481 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3565. Min Range: -6.3565
Max Act: 5.9502. Min Act: -0.1700
Data Index: 4379691 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3565. Min Range: -6.3565
Max Act: 5.9190. Min Act: -0.1700
Data Index: 3498462 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3565. Min Range: -6.3565
Max Act: 5.8877. Min Act: -0.1700
Data Index: 246957 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3565. Min Range: -6.3565
Max Act: 5.8877. Min Act: -0.1700
Data Index: 2406103 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3565. Min Range: -6.3565
Max Act: 5.8877. Min Act: -0.1700
Data Index: 6553030 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3565. Min Range: -6.3565
Max Act: 5.8565. Min Act: -0.1700
Data Index: 7403686 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3565. Min Range: -6.3565
Max Act: 5.7940. Min Act: -0.1700
Data Index: 3257679 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3565. Min Range: -6.3565
Max Act: 5.7940. Min Act: -0.1700
Data Index: 2465120 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3565. Min Range: -6.3565
Max Act: 5.7940. Min Act: -0.1700
Data Index: 969340 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19