Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.9636. Min Act: -0.1700
Data Index: 7645116 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.9011. Min Act: -0.1700
Data Index: 3449857 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.7603. Min Act: -0.1700
Data Index: 5464318 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.7134. Min Act: -0.1700
Data Index: 7472044 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.6978. Min Act: -0.1700
Data Index: 1925560 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.6821. Min Act: -0.1700
Data Index: 3262989 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.6665. Min Act: -0.1700
Data Index: 2118750 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.6508. Min Act: -0.1700
Data Index: 8526006 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.6508. Min Act: -0.1700
Data Index: 1588684 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.6508. Min Act: -0.1700
Data Index: 2927068 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.6352. Min Act: -0.1700
Data Index: 188577 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.6039. Min Act: -0.1700
Data Index: 3281805 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.6039. Min Act: -0.1700
Data Index: 36920 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.6039. Min Act: -0.1700
Data Index: 6949608 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.6039. Min Act: -0.1700
Data Index: 8818066 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.6039. Min Act: -0.1700
Data Index: 7190532 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.6195. Min Act: -0.1700
Data Index: 4122958 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.6039. Min Act: -0.1700
Data Index: 8398999 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.5882. Min Act: -0.1700
Data Index: 6748784 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9636. Min Range: -3.9636
Max Act: 3.5726. Min Act: -0.1700
Data Index: 4467348 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19