Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 975 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.5439. Min Act: -0.1700
Data Index: 556724 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4792. Min Act: -0.1700
Data Index: 449564 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.5278. Min Act: -0.1700
Data Index: 6909 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4954. Min Act: -0.1700
Data Index: 962941 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4954. Min Act: -0.1700
Data Index: 1096034 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4630. Min Act: -0.1700
Data Index: 1198601 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4630. Min Act: -0.1700
Data Index: 613705 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4954. Min Act: -0.1700
Data Index: 196094 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4792. Min Act: -0.1700
Data Index: 1047026 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4142. Min Act: -0.1700
Data Index: 591551 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4304. Min Act: -0.1700
Data Index: 1335736 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4304. Min Act: -0.1700
Data Index: 84449 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4630. Min Act: -0.1700
Data Index: 265126 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4467. Min Act: -0.1700
Data Index: 1052584 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4467. Min Act: -0.1700
Data Index: 889432 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4467. Min Act: -0.1700
Data Index: 964324 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4142. Min Act: -0.1700
Data Index: 1306508 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4304. Min Act: -0.1700
Data Index: 100982 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.4304. Min Act: -0.1700
Data Index: 454468 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5439. Min Range: -2.5439
Max Act: 2.3979. Min Act: -0.1700
Data Index: 1044501 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19