Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3711 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4453. Min Range: -6.4453
Max Act: 6.4453. Min Act: -0.1700
Data Index: 1840480 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4453. Min Range: -6.4453
Max Act: 6.4453. Min Act: -0.1700
Data Index: 1396751 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4453. Min Range: -6.4453
Max Act: 6.3516. Min Act: -0.1700
Data Index: 4965687 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4453. Min Range: -6.4453
Max Act: 6.3516. Min Act: -0.1700
Data Index: 2265057 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4453. Min Range: -6.4453
Max Act: 6.0391. Min Act: -0.1700
Data Index: 5210978 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4453. Min Range: -6.4453
Max Act: 6.0078. Min Act: -0.1700
Data Index: 6918121 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.9453. Min Act: -0.1700
Data Index: 3766291 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.9453. Min Act: -0.1700
Data Index: 1489402 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.9141. Min Act: -0.1700
Data Index: 5454330 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.9141. Min Act: -0.1700
Data Index: 2889351 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.9141. Min Act: -0.1700
Data Index: 3280391 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.8516. Min Act: -0.1700
Data Index: 4089758 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.8516. Min Act: -0.1700
Data Index: 6384400 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.8516. Min Act: -0.1700
Data Index: 8386614 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.8203. Min Act: -0.1700
Data Index: 4798066 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.7578. Min Act: -0.1700
Data Index: 781503 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.7891. Min Act: -0.1700
Data Index: 4820091 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.7578. Min Act: -0.1700
Data Index: 971192 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.7578. Min Act: -0.1700
Data Index: 6454529 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4453. Min Range: -6.4453
Max Act: 5.7578. Min Act: -0.1700
Data Index: 6931377 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19