Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 62 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.5329. Min Range: -2.5329
Max Act: 2.5192. Min Act: -0.0001
Data Index: 823407 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5329. Min Range: -2.5329
Max Act: 2.5329. Min Act: -0.0001
Data Index: 11592 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5329. Min Range: -2.5329
Max Act: 2.4014. Min Act: -0.0001
Data Index: 283446 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5329. Min Range: -2.5329
Max Act: 2.2757. Min Act: -0.0001
Data Index: 11027 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5329. Min Range: -2.5329
Max Act: 2.0349. Min Act: -0.0001
Data Index: 1652659 (Python Code)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5329. Min Range: -2.5329
Max Act: 2.1264. Min Act: -0.0001
Data Index: 1552485 (Python Code)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5329. Min Range: -2.5329
Max Act: 2.1062. Min Act: -0.0001
Data Index: 1424096 (Python Code)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5329. Min Range: -2.5329
Max Act: 2.2765. Min Act: -0.0001
Data Index: 661280 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5329. Min Range: -2.5329
Max Act: 2.0085. Min Act: -0.0001
Data Index: 699018 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5329. Min Range: -2.5329
Max Act: 2.1493. Min Act: -0.0001
Data Index: 1410749 (Python Code)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5329. Min Range: -2.5329
Max Act: 1.8566. Min Act: -0.0001
Data Index: 1543172 (Python Code)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5329. Min Range: -2.5329
Max Act: 2.1801. Min Act: -0.0001
Data Index: 1048217 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5329. Min Range: -2.5329
Max Act: 1.8105. Min Act: -0.0001
Data Index: 1634383 (Python Code)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5329. Min Range: -2.5329
Max Act: 1.6882. Min Act: -0.0001
Data Index: 1485853 (Python Code)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5329. Min Range: -2.5329
Max Act: 1.8593. Min Act: -0.0001
Data Index: 1290106 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5329. Min Range: -2.5329
Max Act: 1.8538. Min Act: -0.0001
Data Index: 309710 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5329. Min Range: -2.5329
Max Act: 1.7521. Min Act: -0.0001
Data Index: 1361306 (Python Code)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5329. Min Range: -2.5329
Max Act: 1.7207. Min Act: -0.0001
Data Index: 957345 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5329. Min Range: -2.5329
Max Act: 1.6300. Min Act: -0.0001
Data Index: 396118 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5329. Min Range: -2.5329
Max Act: 1.6300. Min Act: -0.0001
Data Index: 1228471 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19