Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3121 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.8386. Min Act: -0.0001
Data Index: 254518 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0408. Min Range: -3.0408
Max Act: 3.0408. Min Act: -0.0001
Data Index: 385223 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.5509. Min Act: -0.0001
Data Index: 607792 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.7195. Min Act: -0.0001
Data Index: 646393 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.6549. Min Act: -0.0001
Data Index: 1112048 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.4323. Min Act: -0.0001
Data Index: 1120037 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.4044. Min Act: -0.0001
Data Index: 542329 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.2221. Min Act: -0.0001
Data Index: 26449 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.1959. Min Act: -0.0001
Data Index: 252187 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.1695. Min Act: -0.0001
Data Index: 862497 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.0262. Min Act: -0.0001
Data Index: 52879 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.0451. Min Act: -0.0001
Data Index: 1290680 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.0055. Min Act: -0.0001
Data Index: 1016481 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.1278. Min Act: -0.0001
Data Index: 585931 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.0069. Min Act: -0.0001
Data Index: 1133977 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0408. Min Range: -3.0408
Max Act: 1.9712. Min Act: -0.0001
Data Index: 1290734 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.0791. Min Act: -0.0001
Data Index: 913608 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.1940. Min Act: -0.0001
Data Index: 1129116 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0408. Min Range: -3.0408
Max Act: 1.9446. Min Act: -0.0001
Data Index: 72850 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0408. Min Range: -3.0408
Max Act: 2.0562. Min Act: -0.0001
Data Index: 73164 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19