Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1002 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.2314. Min Act: -0.0001
Data Index: 314756 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.0391. Min Act: -0.0001
Data Index: 452108 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.0609. Min Act: -0.0001
Data Index: 677624 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.1186. Min Act: -0.0001
Data Index: 605630 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.0776. Min Act: -0.0001
Data Index: 941523 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.0722. Min Act: -0.0001
Data Index: 86213 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.0435. Min Act: -0.0001
Data Index: 586334 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.0983. Min Act: -0.0001
Data Index: 179461 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.0148. Min Act: -0.0001
Data Index: 430646 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2314. Min Range: -1.2314
Max Act: 0.9954. Min Act: -0.0001
Data Index: 1497346 (Python Code)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.0239. Min Act: -0.0001
Data Index: 64302 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.0569. Min Act: -0.0001
Data Index: 52270 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2314. Min Range: -1.2314
Max Act: 0.9907. Min Act: -0.0001
Data Index: 1074951 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2314. Min Range: -1.2314
Max Act: 0.9994. Min Act: -0.0001
Data Index: 931648 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.0057. Min Act: -0.0001
Data Index: 117643 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.0268. Min Act: -0.0001
Data Index: 86814 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.0559. Min Act: -0.0001
Data Index: 1148350 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2314. Min Range: -1.2314
Max Act: 0.9588. Min Act: -0.0001
Data Index: 867677 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.0711. Min Act: -0.0001
Data Index: 1592173 (Python Code)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2314. Min Range: -1.2314
Max Act: 1.0074. Min Act: -0.0001
Data Index: 1530501 (Python Code)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19