Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 245 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.8325. Min Act: -0.0001
Data Index: 192875 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.7250. Min Act: -0.0001
Data Index: 231461 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.6669. Min Act: -0.0001
Data Index: 1261344 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.7133. Min Act: -0.0001
Data Index: 707236 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.6389. Min Act: -0.0001
Data Index: 1144764 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.6695. Min Act: -0.0001
Data Index: 296234 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.6401. Min Act: -0.0001
Data Index: 1138846 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.6063. Min Act: -0.0001
Data Index: 1399443 (Python Code)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.6069. Min Act: -0.0001
Data Index: 371864 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.5572. Min Act: -0.0001
Data Index: 807607 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.5777. Min Act: -0.0001
Data Index: 726762 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.5660. Min Act: -0.0001
Data Index: 212139 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.5871. Min Act: -0.0001
Data Index: 83254 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.5409. Min Act: -0.0001
Data Index: 141579 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.5150. Min Act: -0.0001
Data Index: 216164 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.5692. Min Act: -0.0001
Data Index: 1189830 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.5514. Min Act: -0.0001
Data Index: 469964 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.5396. Min Act: -0.0001
Data Index: 1586460 (Python Code)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.5315. Min Act: -0.0001
Data Index: 715006 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8325. Min Range: -0.8325
Max Act: 0.5284. Min Act: -0.0001
Data Index: 396577 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19