Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2047 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6445. Min Range: -6.6445
Max Act: 6.6445. Min Act: -0.1700
Data Index: 3008796 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6445. Min Range: -6.6445
Max Act: 6.2695. Min Act: -0.1700
Data Index: 3502452 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6445. Min Range: -6.6445
Max Act: 6.2383. Min Act: -0.1700
Data Index: 469715 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.9570. Min Act: -0.1700
Data Index: 2401659 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.8945. Min Act: -0.1700
Data Index: 3632008 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.8945. Min Act: -0.1700
Data Index: 4922785 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.8633. Min Act: -0.1700
Data Index: 4100519 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.8633. Min Act: -0.1700
Data Index: 7104181 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.8320. Min Act: -0.1700
Data Index: 4342019 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.8008. Min Act: -0.1700
Data Index: 3216498 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.8320. Min Act: -0.1700
Data Index: 2598774 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.8320. Min Act: -0.1700
Data Index: 3330169 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.8008. Min Act: -0.1700
Data Index: 2449582 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.8008. Min Act: -0.1700
Data Index: 6474813 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.8008. Min Act: -0.1700
Data Index: 7305135 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.8008. Min Act: -0.1700
Data Index: 6662113 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.7695. Min Act: -0.1700
Data Index: 8714623 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.7383. Min Act: -0.1700
Data Index: 2489685 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.7383. Min Act: -0.1700
Data Index: 6005496 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6445. Min Range: -6.6445
Max Act: 5.7383. Min Act: -0.1700
Data Index: 6105833 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19