Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2874 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.3066. Min Act: -0.0001
Data Index: 1169714 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1597. Min Act: -0.0001
Data Index: 1508392 (Python Code)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.9194. Min Act: -0.0001
Data Index: 1577648 (Python Code)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.9543. Min Act: -0.0001
Data Index: 1419097 (Python Code)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.8368. Min Act: -0.0001
Data Index: 1020343 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.8712. Min Act: -0.0001
Data Index: 1516315 (Python Code)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.8007. Min Act: -0.0001
Data Index: 1384181 (Python Code)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.8301. Min Act: -0.0001
Data Index: 1593946 (Python Code)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.7681. Min Act: -0.0001
Data Index: 1420041 (Python Code)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.7888. Min Act: -0.0001
Data Index: 1446994 (Python Code)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.7356. Min Act: -0.0001
Data Index: 1628904 (Python Code)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.7177. Min Act: -0.0000
Data Index: 1467643 (Python Code)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.7580. Min Act: -0.0001
Data Index: 355855 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.7498. Min Act: -0.0000
Data Index: 1338209 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.6834. Min Act: -0.0001
Data Index: 896758 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.6838. Min Act: -0.0000
Data Index: 1504746 (Python Code)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.7320. Min Act: -0.0001
Data Index: 1450644 (Python Code)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.7009. Min Act: -0.0001
Data Index: 1555220 (Python Code)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.5937. Min Act: -0.0001
Data Index: 751858 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3066. Min Range: -2.3066
Max Act: 1.5994. Min Act: -0.0001
Data Index: 1545470 (Python Code)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19