Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6342 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.4487. Min Act: -0.1700
Data Index: 5567884 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.3237. Min Act: -0.1700
Data Index: 4882035 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.1987. Min Act: -0.1700
Data Index: 1761245 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.1987. Min Act: -0.1700
Data Index: 5788166 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.1674. Min Act: -0.1700
Data Index: 1796251 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.0424. Min Act: -0.1700
Data Index: 5608984 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.0424. Min Act: -0.1700
Data Index: 2530425 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.0424. Min Act: -0.1700
Data Index: 8509857 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4487. Min Range: -6.4487
Max Act: 6.0112. Min Act: -0.1700
Data Index: 417681 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4487. Min Range: -6.4487
Max Act: 5.9487. Min Act: -0.1700
Data Index: 2075891 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4487. Min Range: -6.4487
Max Act: 5.9487. Min Act: -0.1700
Data Index: 6695342 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4487. Min Range: -6.4487
Max Act: 5.9174. Min Act: -0.1700
Data Index: 1005463 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4487. Min Range: -6.4487
Max Act: 5.9174. Min Act: -0.1700
Data Index: 6277626 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4487. Min Range: -6.4487
Max Act: 5.9174. Min Act: -0.1700
Data Index: 7942708 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4487. Min Range: -6.4487
Max Act: 5.8862. Min Act: -0.1700
Data Index: 3269658 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4487. Min Range: -6.4487
Max Act: 5.8862. Min Act: -0.1700
Data Index: 8106771 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4487. Min Range: -6.4487
Max Act: 5.8862. Min Act: -0.1700
Data Index: 8184474 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4487. Min Range: -6.4487
Max Act: 5.8549. Min Act: -0.1700
Data Index: 691568 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4487. Min Range: -6.4487
Max Act: 5.8549. Min Act: -0.1700
Data Index: 655657 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4487. Min Range: -6.4487
Max Act: 5.8237. Min Act: -0.1700
Data Index: 2331560 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19