Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5396 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1712. Min Range: -7.1712
Max Act: 7.1712. Min Act: -0.1700
Data Index: 4939490 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1712. Min Range: -7.1712
Max Act: 7.1712. Min Act: -0.1700
Data Index: 7897637 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.9525. Min Act: -0.1700
Data Index: 909620 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.9212. Min Act: -0.1700
Data Index: 3714006 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.8587. Min Act: -0.1700
Data Index: 277196 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.8587. Min Act: -0.1700
Data Index: 8250823 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.8275. Min Act: -0.1700
Data Index: 4621329 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.7962. Min Act: -0.1700
Data Index: 3973800 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.7962. Min Act: -0.1700
Data Index: 2616992 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.7650. Min Act: -0.1700
Data Index: 6213384 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.7650. Min Act: -0.1700
Data Index: 7416450 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.7337. Min Act: -0.1700
Data Index: 673371 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.7337. Min Act: -0.1700
Data Index: 6370771 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.7337. Min Act: -0.1700
Data Index: 2825017 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.7337. Min Act: -0.1700
Data Index: 5268058 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.7337. Min Act: -0.1700
Data Index: 8778721 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.7025. Min Act: -0.1700
Data Index: 3223580 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.7025. Min Act: -0.1700
Data Index: 5217085 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.7025. Min Act: -0.1700
Data Index: 947085 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1712. Min Range: -7.1712
Max Act: 6.6712. Min Act: -0.1700
Data Index: 7321435 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19