Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2316 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0446. Min Act: -0.0001
Data Index: 331178 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0390. Min Act: -0.0001
Data Index: 1595970 (Python Code)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0411. Min Act: -0.0001
Data Index: 969368 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0365. Min Act: -0.0001
Data Index: 1298831 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0387. Min Act: -0.0001
Data Index: 939301 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0379. Min Act: -0.0001
Data Index: 1429549 (Python Code)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0352. Min Act: -0.0001
Data Index: 1526714 (Python Code)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0345. Min Act: -0.0001
Data Index: 1523253 (Python Code)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0362. Min Act: -0.0001
Data Index: 1575371 (Python Code)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0332. Min Act: -0.0001
Data Index: 140137 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0329. Min Act: -0.0001
Data Index: 1478467 (Python Code)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0332. Min Act: -0.0001
Data Index: 1536080 (Python Code)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0338. Min Act: -0.0001
Data Index: 1024411 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0332. Min Act: -0.0001
Data Index: 1547524 (Python Code)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0322. Min Act: -0.0001
Data Index: 1459663 (Python Code)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0310. Min Act: -0.0001
Data Index: 180004 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0307. Min Act: -0.0001
Data Index: 1561570 (Python Code)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0314. Min Act: -0.0001
Data Index: 552585 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0325. Min Act: -0.0001
Data Index: 1253461 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0446. Min Range: -0.0446
Max Act: 0.0337. Min Act: -0.0001
Data Index: 1374221 (Python Code)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19