Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2945 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.6906. Min Act: -0.1700
Data Index: 6497307 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.6437. Min Act: -0.1700
Data Index: 4007266 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.5811. Min Act: -0.1700
Data Index: 4743153 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.5654. Min Act: -0.1700
Data Index: 2947408 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.5498. Min Act: -0.1700
Data Index: 531443 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.5028. Min Act: -0.1700
Data Index: 5288454 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.5184. Min Act: -0.1700
Data Index: 3228706 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.4558. Min Act: -0.1700
Data Index: 6805712 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.4715. Min Act: -0.1700
Data Index: 531444 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.4715. Min Act: -0.1700
Data Index: 4928280 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.4558. Min Act: -0.1700
Data Index: 6382713 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.4401. Min Act: -0.1700
Data Index: 7619760 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.4401. Min Act: -0.1700
Data Index: 3539639 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.4558. Min Act: -0.1700
Data Index: 2171434 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.4401. Min Act: -0.1700
Data Index: 2163268 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.4401. Min Act: -0.1700
Data Index: 1790863 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.4244. Min Act: -0.1700
Data Index: 3342347 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.4088. Min Act: -0.1700
Data Index: 5087437 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.4244. Min Act: -0.1700
Data Index: 725711 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6906. Min Range: -3.6906
Max Act: 3.4244. Min Act: -0.1700
Data Index: 6273319 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19