Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2252. Min Range: -6.2252
Max Act: 6.2252. Min Act: -0.1700
Data Index: 358557 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2252. Min Range: -6.2252
Max Act: 6.1627. Min Act: -0.1700
Data Index: 6302541 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2252. Min Range: -6.2252
Max Act: 6.1940. Min Act: -0.1700
Data Index: 2363060 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2252. Min Range: -6.2252
Max Act: 6.1315. Min Act: -0.1700
Data Index: 8388397 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2252. Min Range: -6.2252
Max Act: 6.0690. Min Act: -0.1700
Data Index: 4099832 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2252. Min Range: -6.2252
Max Act: 6.0377. Min Act: -0.1700
Data Index: 3940120 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2252. Min Range: -6.2252
Max Act: 6.0377. Min Act: -0.1700
Data Index: 3373058 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2252. Min Range: -6.2252
Max Act: 6.0377. Min Act: -0.1700
Data Index: 810493 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2252. Min Range: -6.2252
Max Act: 5.9752. Min Act: -0.1700
Data Index: 3516044 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2252. Min Range: -6.2252
Max Act: 5.9440. Min Act: -0.1700
Data Index: 6803509 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2252. Min Range: -6.2252
Max Act: 5.9440. Min Act: -0.1700
Data Index: 4030784 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2252. Min Range: -6.2252
Max Act: 5.9127. Min Act: -0.1700
Data Index: 3186985 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2252. Min Range: -6.2252
Max Act: 5.9440. Min Act: -0.1700
Data Index: 3343542 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2252. Min Range: -6.2252
Max Act: 5.9127. Min Act: -0.1700
Data Index: 1088426 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2252. Min Range: -6.2252
Max Act: 5.9127. Min Act: -0.1700
Data Index: 2868870 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2252. Min Range: -6.2252
Max Act: 5.8815. Min Act: -0.1700
Data Index: 5866806 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2252. Min Range: -6.2252
Max Act: 5.9127. Min Act: -0.1700
Data Index: 3845437 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2252. Min Range: -6.2252
Max Act: 5.8815. Min Act: -0.1700
Data Index: 362096 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2252. Min Range: -6.2252
Max Act: 5.8815. Min Act: -0.1700
Data Index: 2676522 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2252. Min Range: -6.2252
Max Act: 5.8502. Min Act: -0.1700
Data Index: 4508485 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19