Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3973 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.9127. Min Act: -0.1700
Data Index: 5904873 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.6939. Min Act: -0.1700
Data Index: 8656013 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.6627. Min Act: -0.1700
Data Index: 512437 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.5064. Min Act: -0.1700
Data Index: 8229646 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.4752. Min Act: -0.1700
Data Index: 7962770 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.4439. Min Act: -0.1700
Data Index: 4863581 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.4752. Min Act: -0.1700
Data Index: 5734148 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.3814. Min Act: -0.1700
Data Index: 4921222 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.3189. Min Act: -0.1700
Data Index: 5257309 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.3189. Min Act: -0.1700
Data Index: 8583092 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.2564. Min Act: -0.1700
Data Index: 7821392 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.2252. Min Act: -0.1700
Data Index: 6855731 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.2252. Min Act: -0.1700
Data Index: 208522 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.2252. Min Act: -0.1700
Data Index: 7971837 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.2252. Min Act: -0.1700
Data Index: 8606097 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.1939. Min Act: -0.1700
Data Index: 2487750 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.1627. Min Act: -0.1700
Data Index: 1816142 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.1627. Min Act: -0.1700
Data Index: 5712764 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.1627. Min Act: -0.1700
Data Index: 7232507 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9127. Min Range: -6.9127
Max Act: 6.1627. Min Act: -0.1700
Data Index: 6220131 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19