Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 77 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.5695. Min Act: -0.0001
Data Index: 679262 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.7550. Min Act: -0.0001
Data Index: 211983 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.3541. Min Act: -0.0001
Data Index: 1205839 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.4398. Min Act: -0.0001
Data Index: 683187 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.5301. Min Act: -0.0001
Data Index: 1193320 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.3242. Min Act: -0.0001
Data Index: 242786 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.3972. Min Act: -0.0001
Data Index: 1022090 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.4023. Min Act: -0.0001
Data Index: 889956 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.3643. Min Act: -0.0001
Data Index: 527589 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.2965. Min Act: -0.0001
Data Index: 581360 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.2791. Min Act: -0.0001
Data Index: 1488168 (Python Code)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.2783. Min Act: -0.0001
Data Index: 752697 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.2727. Min Act: -0.0001
Data Index: 610064 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.1334. Min Act: -0.0001
Data Index: 145354 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.2412. Min Act: -0.0001
Data Index: 280262 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.2220. Min Act: -0.0001
Data Index: 972511 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.2149. Min Act: -0.0001
Data Index: 591907 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.0970. Min Act: -0.0001
Data Index: 611121 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7550. Min Range: -2.7550
Max Act: 1.8780. Min Act: -0.0001
Data Index: 1296511 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7550. Min Range: -2.7550
Max Act: 2.3017. Min Act: -0.0001
Data Index: 1347533 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19