Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1664 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.7399. Min Range: -4.7399
Max Act: 4.4888. Min Act: -0.0001
Data Index: 1113520 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7399. Min Range: -4.7399
Max Act: 4.7399. Min Act: -0.0001
Data Index: 467187 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7399. Min Range: -4.7399
Max Act: 4.5315. Min Act: -0.0001
Data Index: 776869 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7399. Min Range: -4.7399
Max Act: 4.3337. Min Act: -0.0001
Data Index: 641131 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7399. Min Range: -4.7399
Max Act: 4.2871. Min Act: -0.0001
Data Index: 1149735 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7399. Min Range: -4.7399
Max Act: 3.7247. Min Act: -0.0001
Data Index: 765274 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7399. Min Range: -4.7399
Max Act: 3.7285. Min Act: -0.0001
Data Index: 1193567 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7399. Min Range: -4.7399
Max Act: 3.6168. Min Act: -0.0001
Data Index: 741942 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7399. Min Range: -4.7399
Max Act: 3.4532. Min Act: -0.0001
Data Index: 117954 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7399. Min Range: -4.7399
Max Act: 3.8440. Min Act: -0.0001
Data Index: 405943 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7399. Min Range: -4.7399
Max Act: 2.9526. Min Act: -0.0001
Data Index: 774798 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7399. Min Range: -4.7399
Max Act: 3.6334. Min Act: -0.0001
Data Index: 1004287 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7399. Min Range: -4.7399
Max Act: 3.1617. Min Act: -0.0001
Data Index: 862738 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7399. Min Range: -4.7399
Max Act: 3.4354. Min Act: -0.0001
Data Index: 276785 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7399. Min Range: -4.7399
Max Act: 3.3713. Min Act: -0.0001
Data Index: 1130378 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7399. Min Range: -4.7399
Max Act: 3.3952. Min Act: -0.0001
Data Index: 1149989 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7399. Min Range: -4.7399
Max Act: 3.1937. Min Act: -0.0001
Data Index: 42514 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7399. Min Range: -4.7399
Max Act: 3.4963. Min Act: -0.0001
Data Index: 737038 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7399. Min Range: -4.7399
Max Act: 3.4486. Min Act: -0.0001
Data Index: 518223 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7399. Min Range: -4.7399
Max Act: 3.1638. Min Act: -0.0001
Data Index: 1280180 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19