Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2994 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.7006. Min Range: -2.7006
Max Act: 2.7006. Min Act: -0.0001
Data Index: 1039709 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7006. Min Range: -2.7006
Max Act: 2.5473. Min Act: -0.0001
Data Index: 668557 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7006. Min Range: -2.7006
Max Act: 2.6330. Min Act: -0.0001
Data Index: 1161106 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7006. Min Range: -2.7006
Max Act: 2.2473. Min Act: -0.0001
Data Index: 289307 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7006. Min Range: -2.7006
Max Act: 2.0989. Min Act: -0.0001
Data Index: 284688 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7006. Min Range: -2.7006
Max Act: 1.8505. Min Act: -0.0001
Data Index: 677037 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7006. Min Range: -2.7006
Max Act: 1.8454. Min Act: -0.0001
Data Index: 54765 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7006. Min Range: -2.7006
Max Act: 1.8982. Min Act: -0.0001
Data Index: 1446144 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7006. Min Range: -2.7006
Max Act: 1.8682. Min Act: -0.0001
Data Index: 1045636 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7006. Min Range: -2.7006
Max Act: 1.7011. Min Act: -0.0001
Data Index: 391905 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7006. Min Range: -2.7006
Max Act: 1.7453. Min Act: -0.0001
Data Index: 1540930 (Python Code)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7006. Min Range: -2.7006
Max Act: 1.7130. Min Act: -0.0001
Data Index: 962027 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7006. Min Range: -2.7006
Max Act: 1.6973. Min Act: -0.0001
Data Index: 38873 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7006. Min Range: -2.7006
Max Act: 1.7223. Min Act: -0.0001
Data Index: 696866 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7006. Min Range: -2.7006
Max Act: 1.7321. Min Act: -0.0001
Data Index: 265225 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7006. Min Range: -2.7006
Max Act: 1.7653. Min Act: -0.0001
Data Index: 1268507 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7006. Min Range: -2.7006
Max Act: 1.6228. Min Act: -0.0001
Data Index: 1311566 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7006. Min Range: -2.7006
Max Act: 1.5242. Min Act: -0.0001
Data Index: 982051 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7006. Min Range: -2.7006
Max Act: 1.4918. Min Act: -0.0001
Data Index: 1045685 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7006. Min Range: -2.7006
Max Act: 1.5224. Min Act: -0.0001
Data Index: 1230377 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19