Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1946 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0496. Min Range: -2.0496
Max Act: 2.0496. Min Act: -0.0001
Data Index: 240809 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.6908. Min Act: -0.0001
Data Index: 428031 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.5722. Min Act: -0.0001
Data Index: 166729 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.7183. Min Act: -0.0001
Data Index: 197125 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.5315. Min Act: -0.0001
Data Index: 1353951 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.5869. Min Act: -0.0001
Data Index: 446604 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.7974. Min Act: -0.0001
Data Index: 731690 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.6275. Min Act: -0.0001
Data Index: 32830 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.7055. Min Act: -0.0001
Data Index: 239963 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.5069. Min Act: -0.0001
Data Index: 1391144 (Python Code)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.4708. Min Act: -0.0001
Data Index: 1618886 (Python Code)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.5659. Min Act: -0.0001
Data Index: 482032 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.3826. Min Act: -0.0001
Data Index: 1407917 (Python Code)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.4613. Min Act: -0.0001
Data Index: 1503597 (Python Code)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.4529. Min Act: -0.0001
Data Index: 1447677 (Python Code)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.5018. Min Act: -0.0001
Data Index: 833533 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.4625. Min Act: -0.0001
Data Index: 1622823 (Python Code)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.3205. Min Act: -0.0001
Data Index: 1465403 (Python Code)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.4311. Min Act: -0.0001
Data Index: 1554608 (Python Code)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0496. Min Range: -2.0496
Max Act: 1.4230. Min Act: -0.0001
Data Index: 1517257 (Python Code)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19