Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2258 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.6613. Min Act: -0.0001
Data Index: 1529714 (Python Code)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.6427. Min Act: -0.0001
Data Index: 1431399 (Python Code)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.6444. Min Act: -0.0001
Data Index: 260803 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.6449. Min Act: -0.0001
Data Index: 1555067 (Python Code)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.6047. Min Act: -0.0001
Data Index: 516675 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.6194. Min Act: -0.0001
Data Index: 56331 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.5602. Min Act: -0.0001
Data Index: 729645 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.5650. Min Act: -0.0001
Data Index: 1479509 (Python Code)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.5610. Min Act: -0.0001
Data Index: 1235924 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.5342. Min Act: -0.0001
Data Index: 1220372 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.5169. Min Act: -0.0001
Data Index: 859878 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.5216. Min Act: -0.0001
Data Index: 571040 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.5595. Min Act: -0.0001
Data Index: 1451109 (Python Code)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.5198. Min Act: -0.0001
Data Index: 1572471 (Python Code)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.5414. Min Act: -0.0001
Data Index: 800087 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.4842. Min Act: -0.0001
Data Index: 901135 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.4831. Min Act: -0.0001
Data Index: 339020 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.5469. Min Act: -0.0001
Data Index: 551958 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.5399. Min Act: -0.0001
Data Index: 1446058 (Python Code)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6613. Min Range: -0.6613
Max Act: 0.5312. Min Act: -0.0001
Data Index: 836203 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19