Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2574 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.6527. Min Act: -0.1700
Data Index: 2119066 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.6215. Min Act: -0.1700
Data Index: 4529015 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.5277. Min Act: -0.1700
Data Index: 5090068 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.4965. Min Act: -0.1700
Data Index: 1153240 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.4340. Min Act: -0.1700
Data Index: 3270575 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.4340. Min Act: -0.1700
Data Index: 6201594 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.4652. Min Act: -0.1700
Data Index: 6355497 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.4027. Min Act: -0.1700
Data Index: 7855946 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.4340. Min Act: -0.1700
Data Index: 6633789 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.3715. Min Act: -0.1700
Data Index: 3337514 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.3715. Min Act: -0.1700
Data Index: 657251 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.3402. Min Act: -0.1700
Data Index: 796773 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.3090. Min Act: -0.1700
Data Index: 660790 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.3402. Min Act: -0.1700
Data Index: 8576263 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.3090. Min Act: -0.1700
Data Index: 1803973 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.3402. Min Act: -0.1700
Data Index: 4139369 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.3090. Min Act: -0.1700
Data Index: 7710544 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.2777. Min Act: -0.1700
Data Index: 4921069 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.2777. Min Act: -0.1700
Data Index: 8542707 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6527. Min Range: -6.6527
Max Act: 6.2777. Min Act: -0.1700
Data Index: 7557320 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19