Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3673 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.8309. Min Act: -0.0001
Data Index: 51076 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.6726. Min Act: -0.0001
Data Index: 117411 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.3338. Min Act: -0.0001
Data Index: 978117 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.3800. Min Act: -0.0001
Data Index: 324491 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.5040. Min Act: -0.0001
Data Index: 908853 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.2686. Min Act: -0.0001
Data Index: 122487 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.4281. Min Act: -0.0001
Data Index: 54049 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.3103. Min Act: -0.0001
Data Index: 1331134 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.3790. Min Act: -0.0001
Data Index: 1248114 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.3055. Min Act: -0.0001
Data Index: 386318 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.2280. Min Act: -0.0001
Data Index: 1028727 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.3454. Min Act: -0.0001
Data Index: 1260422 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.1952. Min Act: -0.0001
Data Index: 203102 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.1859. Min Act: -0.0001
Data Index: 1083538 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.3106. Min Act: -0.0001
Data Index: 1091841 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.2713. Min Act: -0.0001
Data Index: 1189653 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.2335. Min Act: -0.0001
Data Index: 840796 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.3032. Min Act: -0.0001
Data Index: 897262 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.2925. Min Act: -0.0001
Data Index: 1017509 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8309. Min Range: -1.8309
Max Act: 1.1937. Min Act: -0.0001
Data Index: 453308 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19