Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2069 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.4590. Min Range: -1.4590
Max Act: 1.4590. Min Act: -0.0001
Data Index: 510117 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4590. Min Range: -1.4590
Max Act: 1.2761. Min Act: -0.0001
Data Index: 229229 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4590. Min Range: -1.4590
Max Act: 1.1710. Min Act: -0.0001
Data Index: 1161780 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4590. Min Range: -1.4590
Max Act: 1.1299. Min Act: -0.0001
Data Index: 346463 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4590. Min Range: -1.4590
Max Act: 1.1307. Min Act: -0.0001
Data Index: 1095039 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4590. Min Range: -1.4590
Max Act: 1.0598. Min Act: -0.0001
Data Index: 1157032 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4590. Min Range: -1.4590
Max Act: 1.0631. Min Act: -0.0001
Data Index: 32440 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4590. Min Range: -1.4590
Max Act: 1.0071. Min Act: -0.0001
Data Index: 1076283 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4590. Min Range: -1.4590
Max Act: 1.0127. Min Act: -0.0001
Data Index: 629258 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4590. Min Range: -1.4590
Max Act: 1.0461. Min Act: -0.0001
Data Index: 450407 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4590. Min Range: -1.4590
Max Act: 1.1056. Min Act: -0.0001
Data Index: 1047342 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4590. Min Range: -1.4590
Max Act: 1.0333. Min Act: -0.0001
Data Index: 1266690 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4590. Min Range: -1.4590
Max Act: 0.9439. Min Act: -0.0001
Data Index: 213709 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4590. Min Range: -1.4590
Max Act: 0.9451. Min Act: -0.0001
Data Index: 776698 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4590. Min Range: -1.4590
Max Act: 1.0090. Min Act: -0.0001
Data Index: 229844 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4590. Min Range: -1.4590
Max Act: 0.9644. Min Act: -0.0001
Data Index: 780017 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4590. Min Range: -1.4590
Max Act: 0.8770. Min Act: -0.0001
Data Index: 328824 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4590. Min Range: -1.4590
Max Act: 0.9451. Min Act: -0.0001
Data Index: 81341 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4590. Min Range: -1.4590
Max Act: 0.9347. Min Act: -0.0001
Data Index: 525993 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4590. Min Range: -1.4590
Max Act: 0.9343. Min Act: -0.0001
Data Index: 670252 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19