Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1630 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.7208. Min Act: -0.0001
Data Index: 1419015 (Python Code)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.5569. Min Act: -0.0001
Data Index: 1528512 (Python Code)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.6597. Min Act: -0.0001
Data Index: 1398450 (Python Code)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.4673. Min Act: -0.0001
Data Index: 48120 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.3958. Min Act: -0.0001
Data Index: 1509754 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.2247. Min Act: -0.0001
Data Index: 421557 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.3425. Min Act: -0.0001
Data Index: 1555643 (Python Code)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.1615. Min Act: -0.0001
Data Index: 721756 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.1816. Min Act: -0.0001
Data Index: 518488 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.2418. Min Act: -0.0001
Data Index: 89755 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.1436. Min Act: -0.0001
Data Index: 1554031 (Python Code)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.2183. Min Act: -0.0001
Data Index: 219077 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.1799. Min Act: -0.0001
Data Index: 1071550 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.1743. Min Act: -0.0001
Data Index: 1041632 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.1351. Min Act: -0.0001
Data Index: 546320 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.1951. Min Act: -0.0001
Data Index: 779865 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.0407. Min Act: -0.0001
Data Index: 961207 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.1422. Min Act: -0.0001
Data Index: 1276231 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.1535. Min Act: -0.0001
Data Index: 566950 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7208. Min Range: -1.7208
Max Act: 1.1379. Min Act: -0.0001
Data Index: 1061825 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19