Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3338 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.6393. Min Range: -2.6393
Max Act: 2.6393. Min Act: -0.0001
Data Index: 1630496 (Python Code)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.5708. Min Act: -0.0001
Data Index: 154242 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.5483. Min Act: -0.0001
Data Index: 174300 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.8281. Min Act: -0.0001
Data Index: 1307783 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.5315. Min Act: -0.0000
Data Index: 102602 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.6054. Min Act: -0.0001
Data Index: 1585361 (Python Code)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.5608. Min Act: -0.0001
Data Index: 659095 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.4207. Min Act: -0.0001
Data Index: 1457954 (Python Code)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.1102. Min Act: -0.0001
Data Index: 350086 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.3425. Min Act: -0.0001
Data Index: 465893 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.2425. Min Act: -0.0001
Data Index: 1314442 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.3089. Min Act: -0.0001
Data Index: 254515 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.3715. Min Act: -0.0001
Data Index: 208598 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.3736. Min Act: -0.0001
Data Index: 1146303 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.1928. Min Act: -0.0001
Data Index: 50911 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.2772. Min Act: -0.0001
Data Index: 1423912 (Python Code)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.1858. Min Act: -0.0001
Data Index: 984039 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.2259. Min Act: -0.0001
Data Index: 721047 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.1344. Min Act: -0.0000
Data Index: 998828 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6393. Min Range: -2.6393
Max Act: 1.2176. Min Act: -0.0001
Data Index: 661404 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19