Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2019 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.3935. Min Range: -1.3935
Max Act: 1.3935. Min Act: -0.0001
Data Index: 32261 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3935. Min Range: -1.3935
Max Act: 1.3702. Min Act: -0.0001
Data Index: 1008474 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3935. Min Range: -1.3935
Max Act: 1.3349. Min Act: -0.0001
Data Index: 1090838 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3935. Min Range: -1.3935
Max Act: 1.3205. Min Act: -0.0001
Data Index: 787164 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3935. Min Range: -1.3935
Max Act: 1.1679. Min Act: -0.0001
Data Index: 279365 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3935. Min Range: -1.3935
Max Act: 1.1256. Min Act: -0.0001
Data Index: 369317 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3935. Min Range: -1.3935
Max Act: 1.1012. Min Act: -0.0001
Data Index: 350906 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3935. Min Range: -1.3935
Max Act: 1.0695. Min Act: -0.0001
Data Index: 728345 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3935. Min Range: -1.3935
Max Act: 1.0886. Min Act: -0.0001
Data Index: 497965 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3935. Min Range: -1.3935
Max Act: 0.9389. Min Act: -0.0001
Data Index: 816315 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3935. Min Range: -1.3935
Max Act: 0.9634. Min Act: -0.0001
Data Index: 1376688 (Python Code)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3935. Min Range: -1.3935
Max Act: 1.0017. Min Act: -0.0001
Data Index: 1012562 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3935. Min Range: -1.3935
Max Act: 0.9434. Min Act: -0.0001
Data Index: 1644076 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3935. Min Range: -1.3935
Max Act: 0.9403. Min Act: -0.0001
Data Index: 554077 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3935. Min Range: -1.3935
Max Act: 0.9700. Min Act: -0.0001
Data Index: 1340195 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3935. Min Range: -1.3935
Max Act: 0.9346. Min Act: -0.0001
Data Index: 202546 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3935. Min Range: -1.3935
Max Act: 0.9363. Min Act: -0.0001
Data Index: 733726 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3935. Min Range: -1.3935
Max Act: 0.9623. Min Act: -0.0001
Data Index: 733285 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3935. Min Range: -1.3935
Max Act: 0.9233. Min Act: -0.0001
Data Index: 942116 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3935. Min Range: -1.3935
Max Act: 0.8927. Min Act: -0.0001
Data Index: 1176186 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19