Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6135 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.7806. Min Range: -2.7806
Max Act: 2.7806. Min Act: -0.0001
Data Index: 290565 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7806. Min Range: -2.7806
Max Act: 2.6524. Min Act: -0.0001
Data Index: 1140200 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7806. Min Range: -2.7806
Max Act: 2.5347. Min Act: -0.0001
Data Index: 820315 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7806. Min Range: -2.7806
Max Act: 2.5203. Min Act: -0.0001
Data Index: 227099 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7806. Min Range: -2.7806
Max Act: 2.2446. Min Act: -0.0001
Data Index: 560004 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7806. Min Range: -2.7806
Max Act: 2.1563. Min Act: -0.0001
Data Index: 375371 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7806. Min Range: -2.7806
Max Act: 2.1455. Min Act: -0.0001
Data Index: 676556 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7806. Min Range: -2.7806
Max Act: 2.0277. Min Act: -0.0001
Data Index: 1240806 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7806. Min Range: -2.7806
Max Act: 2.2010. Min Act: -0.0001
Data Index: 768478 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7806. Min Range: -2.7806
Max Act: 2.1027. Min Act: -0.0001
Data Index: 1121897 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7806. Min Range: -2.7806
Max Act: 1.9864. Min Act: -0.0001
Data Index: 106034 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7806. Min Range: -2.7806
Max Act: 1.8420. Min Act: -0.0001
Data Index: 329339 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7806. Min Range: -2.7806
Max Act: 1.9193. Min Act: -0.0001
Data Index: 377586 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7806. Min Range: -2.7806
Max Act: 1.9082. Min Act: -0.0001
Data Index: 1008892 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7806. Min Range: -2.7806
Max Act: 1.9309. Min Act: -0.0001
Data Index: 1242232 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7806. Min Range: -2.7806
Max Act: 2.0133. Min Act: -0.0001
Data Index: 493635 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7806. Min Range: -2.7806
Max Act: 1.9197. Min Act: -0.0001
Data Index: 667871 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7806. Min Range: -2.7806
Max Act: 1.9868. Min Act: -0.0001
Data Index: 338457 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7806. Min Range: -2.7806
Max Act: 2.0185. Min Act: -0.0001
Data Index: 405347 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7806. Min Range: -2.7806
Max Act: 2.2096. Min Act: -0.0001
Data Index: 796105 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19