Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2794 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2618. Min Range: -5.2618
Max Act: 5.2618. Min Act: -0.1700
Data Index: 4951525 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2618. Min Range: -5.2618
Max Act: 5.1993. Min Act: -0.1700
Data Index: 4308277 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2618. Min Range: -5.2618
Max Act: 5.1681. Min Act: -0.1700
Data Index: 8468291 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2618. Min Range: -5.2618
Max Act: 5.1368. Min Act: -0.1700
Data Index: 2325893 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2618. Min Range: -5.2618
Max Act: 5.1056. Min Act: -0.1700
Data Index: 1792377 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2618. Min Range: -5.2618
Max Act: 5.1056. Min Act: -0.1700
Data Index: 4497125 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2618. Min Range: -5.2618
Max Act: 5.1368. Min Act: -0.1700
Data Index: 8267423 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2618. Min Range: -5.2618
Max Act: 5.0743. Min Act: -0.1700
Data Index: 7482125 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2618. Min Range: -5.2618
Max Act: 5.0431. Min Act: -0.1700
Data Index: 2111452 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2618. Min Range: -5.2618
Max Act: 5.0431. Min Act: -0.1700
Data Index: 4240425 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2618. Min Range: -5.2618
Max Act: 4.9806. Min Act: -0.1700
Data Index: 3556355 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2618. Min Range: -5.2618
Max Act: 4.9806. Min Act: -0.1700
Data Index: 4115838 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2618. Min Range: -5.2618
Max Act: 4.9806. Min Act: -0.1700
Data Index: 5251579 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2618. Min Range: -5.2618
Max Act: 4.9493. Min Act: -0.1700
Data Index: 4427746 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2618. Min Range: -5.2618
Max Act: 4.9493. Min Act: -0.1700
Data Index: 4475076 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2618. Min Range: -5.2618
Max Act: 4.9181. Min Act: -0.1700
Data Index: 4115262 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2618. Min Range: -5.2618
Max Act: 4.9181. Min Act: -0.1700
Data Index: 3894245 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2618. Min Range: -5.2618
Max Act: 4.8868. Min Act: -0.1700
Data Index: 5899409 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2618. Min Range: -5.2618
Max Act: 4.8868. Min Act: -0.1700
Data Index: 1385942 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2618. Min Range: -5.2618
Max Act: 4.8868. Min Act: -0.1700
Data Index: 6648140 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19