Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2526 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.5996. Min Act: -0.0001
Data Index: 1412546 (Python Code)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.3413. Min Act: -0.0001
Data Index: 1307211 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.4062. Min Act: -0.0001
Data Index: 1202058 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.2424. Min Act: -0.0001
Data Index: 944440 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.3241. Min Act: -0.0001
Data Index: 60101 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.2601. Min Act: -0.0001
Data Index: 3360 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.3153. Min Act: -0.0001
Data Index: 261924 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.1458. Min Act: -0.0001
Data Index: 1312890 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.1743. Min Act: -0.0001
Data Index: 1309220 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.1774. Min Act: -0.0001
Data Index: 144303 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.0523. Min Act: -0.0001
Data Index: 1242247 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.0914. Min Act: -0.0001
Data Index: 484236 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.1074. Min Act: -0.0001
Data Index: 1004108 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.1083. Min Act: -0.0001
Data Index: 462692 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.1671. Min Act: -0.0001
Data Index: 456354 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.1672. Min Act: -0.0001
Data Index: 1361777 (Python Code)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.1117. Min Act: -0.0001
Data Index: 361179 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.1289. Min Act: -0.0001
Data Index: 700314 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.1222. Min Act: -0.0001
Data Index: 868870 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5996. Min Range: -1.5996
Max Act: 1.0945. Min Act: -0.0001
Data Index: 1357618 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19