Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3451. Min Range: -6.3451
Max Act: 6.3451. Min Act: -0.1700
Data Index: 3181643 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3451. Min Range: -6.3451
Max Act: 6.1264. Min Act: -0.1700
Data Index: 3181642 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3451. Min Range: -6.3451
Max Act: 6.0014. Min Act: -0.1700
Data Index: 2511251 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3451. Min Range: -6.3451
Max Act: 6.0014. Min Act: -0.1700
Data Index: 1214620 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3451. Min Range: -6.3451
Max Act: 6.0014. Min Act: -0.1700
Data Index: 241070 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3451. Min Range: -6.3451
Max Act: 5.9701. Min Act: -0.1700
Data Index: 3021803 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3451. Min Range: -6.3451
Max Act: 5.9389. Min Act: -0.1700
Data Index: 8564016 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3451. Min Range: -6.3451
Max Act: 5.9389. Min Act: -0.1700
Data Index: 4556450 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3451. Min Range: -6.3451
Max Act: 5.9076. Min Act: -0.1700
Data Index: 4066533 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3451. Min Range: -6.3451
Max Act: 5.9076. Min Act: -0.1700
Data Index: 1585395 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3451. Min Range: -6.3451
Max Act: 5.9389. Min Act: -0.1700
Data Index: 4556448 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3451. Min Range: -6.3451
Max Act: 5.8451. Min Act: -0.1700
Data Index: 2402503 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3451. Min Range: -6.3451
Max Act: 5.8764. Min Act: -0.1700
Data Index: 4970542 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3451. Min Range: -6.3451
Max Act: 5.8764. Min Act: -0.1700
Data Index: 7067625 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3451. Min Range: -6.3451
Max Act: 5.8139. Min Act: -0.1700
Data Index: 8333729 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3451. Min Range: -6.3451
Max Act: 5.8451. Min Act: -0.1700
Data Index: 1252395 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3451. Min Range: -6.3451
Max Act: 5.8451. Min Act: -0.1700
Data Index: 7420979 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3451. Min Range: -6.3451
Max Act: 5.8451. Min Act: -0.1700
Data Index: 7556176 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3451. Min Range: -6.3451
Max Act: 5.8451. Min Act: -0.1700
Data Index: 549868 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3451. Min Range: -6.3451
Max Act: 5.8451. Min Act: -0.1700
Data Index: 8435756 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19