Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1120 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.4569. Min Act: -0.1700
Data Index: 828925 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.4569. Min Act: -0.1700
Data Index: 1294697 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.4569. Min Act: -0.1699
Data Index: 1285991 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.3631. Min Act: -0.1700
Data Index: 354286 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.3631. Min Act: -0.1700
Data Index: 350014 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.3631. Min Act: -0.1700
Data Index: 56740 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.4256. Min Act: -0.1700
Data Index: 1169982 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.3318. Min Act: -0.1700
Data Index: 850463 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.3631. Min Act: -0.1700
Data Index: 253758 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.2381. Min Act: -0.1700
Data Index: 1348525 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.2693. Min Act: -0.1699
Data Index: 175330 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.2068. Min Act: -0.1700
Data Index: 33407 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.2381. Min Act: -0.1700
Data Index: 1262987 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.2381. Min Act: -0.1700
Data Index: 557720 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.2381. Min Act: -0.1700
Data Index: 1314743 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.1756. Min Act: -0.1700
Data Index: 4925 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.2381. Min Act: -0.1700
Data Index: 949479 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.2068. Min Act: -0.1700
Data Index: 1107481 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.2068. Min Act: -0.1700
Data Index: 641851 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4569. Min Range: -5.4569
Max Act: 5.2068. Min Act: -0.1700
Data Index: 267531 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19