Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2665 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.5305. Min Range: -2.5305
Max Act: 2.5305. Min Act: -0.0001
Data Index: 1497456 (Python Code)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5305. Min Range: -2.5305
Max Act: 2.1479. Min Act: -0.0001
Data Index: 1506795 (Python Code)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5305. Min Range: -2.5305
Max Act: 2.1200. Min Act: -0.0001
Data Index: 1516086 (Python Code)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5305. Min Range: -2.5305
Max Act: 2.1117. Min Act: -0.0001
Data Index: 1367049 (Python Code)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5305. Min Range: -2.5305
Max Act: 2.1271. Min Act: -0.0001
Data Index: 1532349 (Python Code)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5305. Min Range: -2.5305
Max Act: 2.0325. Min Act: -0.0001
Data Index: 1399203 (Python Code)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5305. Min Range: -2.5305
Max Act: 1.8511. Min Act: -0.0001
Data Index: 1645734 (Python Code)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5305. Min Range: -2.5305
Max Act: 1.8918. Min Act: -0.0001
Data Index: 1440734 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5305. Min Range: -2.5305
Max Act: 1.8725. Min Act: -0.0001
Data Index: 1631259 (Python Code)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5305. Min Range: -2.5305
Max Act: 1.8192. Min Act: -0.0001
Data Index: 1452599 (Python Code)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5305. Min Range: -2.5305
Max Act: 1.7884. Min Act: -0.0001
Data Index: 1408972 (Python Code)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5305. Min Range: -2.5305
Max Act: 1.7185. Min Act: -0.0001
Data Index: 1498893 (Python Code)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5305. Min Range: -2.5305
Max Act: 1.8040. Min Act: -0.0001
Data Index: 1506173 (Python Code)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5305. Min Range: -2.5305
Max Act: 1.7553. Min Act: -0.0001
Data Index: 1565378 (Python Code)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5305. Min Range: -2.5305
Max Act: 1.7294. Min Act: -0.0001
Data Index: 813281 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5305. Min Range: -2.5305
Max Act: 1.7418. Min Act: -0.0001
Data Index: 1620060 (Python Code)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5305. Min Range: -2.5305
Max Act: 1.7869. Min Act: -0.0001
Data Index: 1415100 (Python Code)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5305. Min Range: -2.5305
Max Act: 1.7269. Min Act: -0.0001
Data Index: 1487723 (Python Code)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5305. Min Range: -2.5305
Max Act: 1.6536. Min Act: -0.0001
Data Index: 1567429 (Python Code)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5305. Min Range: -2.5305
Max Act: 1.6986. Min Act: -0.0001
Data Index: 1480167 (Python Code)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19