Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2556 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.5249. Min Act: -0.0001
Data Index: 678802 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.5361. Min Act: -0.0001
Data Index: 142332 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.5500. Min Act: -0.0001
Data Index: 360825 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.5119. Min Act: -0.0001
Data Index: 737511 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.5058. Min Act: -0.0001
Data Index: 962195 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.5292. Min Act: -0.0001
Data Index: 747361 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.5090. Min Act: -0.0001
Data Index: 352651 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.5106. Min Act: -0.0001
Data Index: 420915 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.5058. Min Act: -0.0001
Data Index: 221997 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.4817. Min Act: -0.0001
Data Index: 1028075 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.4876. Min Act: -0.0001
Data Index: 913282 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.4681. Min Act: -0.0001
Data Index: 1061336 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.4796. Min Act: -0.0001
Data Index: 642801 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.4309. Min Act: -0.0001
Data Index: 781347 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.4571. Min Act: -0.0001
Data Index: 983894 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.4585. Min Act: -0.0001
Data Index: 1122279 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.4517. Min Act: -0.0001
Data Index: 923305 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.4496. Min Act: -0.0001
Data Index: 259869 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.4367. Min Act: -0.0001
Data Index: 770111 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5500. Min Range: -0.5500
Max Act: 0.4484. Min Act: -0.0001
Data Index: 596815 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19