Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2527 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1527. Min Range: -5.1527
Max Act: 5.1527. Min Act: -0.1700
Data Index: 2832927 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1527. Min Range: -5.1527
Max Act: 5.0277. Min Act: -0.1700
Data Index: 5280108 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1527. Min Range: -5.1527
Max Act: 5.0590. Min Act: -0.1700
Data Index: 1553759 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.9965. Min Act: -0.1700
Data Index: 3744844 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1527. Min Range: -5.1527
Max Act: 5.0277. Min Act: -0.1700
Data Index: 1647251 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.9965. Min Act: -0.1700
Data Index: 6216936 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.9652. Min Act: -0.1700
Data Index: 6163876 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.9652. Min Act: -0.1700
Data Index: 3607102 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.9652. Min Act: -0.1700
Data Index: 8310524 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.9340. Min Act: -0.1700
Data Index: 5073510 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.9652. Min Act: -0.1700
Data Index: 3995488 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.9340. Min Act: -0.1700
Data Index: 3843165 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.9340. Min Act: -0.1700
Data Index: 2167564 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.9027. Min Act: -0.1700
Data Index: 4751378 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.9027. Min Act: -0.1700
Data Index: 2500534 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.9027. Min Act: -0.1700
Data Index: 6735080 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.9027. Min Act: -0.1700
Data Index: 3551365 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.8715. Min Act: -0.1700
Data Index: 397346 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.9027. Min Act: -0.1700
Data Index: 2992521 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1527. Min Range: -5.1527
Max Act: 4.9027. Min Act: -0.1700
Data Index: 2788814 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19