Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3937 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0149. Min Range: -2.0149
Max Act: 2.0149. Min Act: -0.0001
Data Index: 1600609 (Python Code)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.6926. Min Act: -0.0001
Data Index: 1417396 (Python Code)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.5088. Min Act: -0.0001
Data Index: 1430422 (Python Code)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.4828. Min Act: -0.0001
Data Index: 1384435 (Python Code)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.5208. Min Act: -0.0001
Data Index: 1468178 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.4845. Min Act: -0.0001
Data Index: 1078592 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.4568. Min Act: -0.0001
Data Index: 1373720 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.4087. Min Act: -0.0001
Data Index: 1377411 (Python Code)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.4599. Min Act: -0.0001
Data Index: 1397831 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.5538. Min Act: -0.0001
Data Index: 588996 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.4317. Min Act: -0.0001
Data Index: 1391745 (Python Code)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.4266. Min Act: -0.0001
Data Index: 1586537 (Python Code)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.3605. Min Act: -0.0001
Data Index: 1537641 (Python Code)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.3835. Min Act: -0.0001
Data Index: 1480557 (Python Code)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.3487. Min Act: -0.0001
Data Index: 1507515 (Python Code)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.3371. Min Act: -0.0001
Data Index: 1624563 (Python Code)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.2476. Min Act: -0.0001
Data Index: 1442247 (Python Code)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.3146. Min Act: -0.0001
Data Index: 1539291 (Python Code)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.3394. Min Act: -0.0001
Data Index: 1534843 (Python Code)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0149. Min Range: -2.0149
Max Act: 1.2639. Min Act: -0.0001
Data Index: 1463725 (Python Code)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19