Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2424 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.3203. Min Act: -0.0001
Data Index: 855379 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.3320. Min Act: -0.0001
Data Index: 1484 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.3496. Min Act: -0.0001
Data Index: 1138569 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.2880. Min Act: -0.0001
Data Index: 1260598 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.3104. Min Act: -0.0001
Data Index: 519928 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.3060. Min Act: -0.0001
Data Index: 947932 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.3201. Min Act: -0.0001
Data Index: 1601666 (Python Code)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.2698. Min Act: -0.0001
Data Index: 306067 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.2730. Min Act: -0.0001
Data Index: 815707 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.2614. Min Act: -0.0001
Data Index: 1001162 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.2839. Min Act: -0.0001
Data Index: 619602 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.2343. Min Act: -0.0001
Data Index: 586724 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.2489. Min Act: -0.0001
Data Index: 282092 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.2563. Min Act: -0.0001
Data Index: 383981 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.2839. Min Act: -0.0001
Data Index: 1024437 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.2385. Min Act: -0.0001
Data Index: 1114092 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.2360. Min Act: -0.0001
Data Index: 1532716 (Python Code)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.2435. Min Act: -0.0001
Data Index: 1274409 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.2414. Min Act: -0.0001
Data Index: 131291 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3496. Min Range: -0.3496
Max Act: 0.2438. Min Act: -0.0001
Data Index: 309091 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19