Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2450 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.8091. Min Act: -0.0001
Data Index: 709154 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.7384. Min Act: -0.0001
Data Index: 1107987 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.8361. Min Act: -0.0001
Data Index: 96180 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.7325. Min Act: -0.0001
Data Index: 1345941 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.7721. Min Act: -0.0001
Data Index: 794141 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.7379. Min Act: -0.0001
Data Index: 1297465 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.8135. Min Act: -0.0001
Data Index: 1274727 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.7556. Min Act: -0.0001
Data Index: 1179669 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.7121. Min Act: -0.0001
Data Index: 228336 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.6831. Min Act: -0.0001
Data Index: 1008720 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.7798. Min Act: -0.0001
Data Index: 866137 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.7831. Min Act: -0.0001
Data Index: 285483 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.7184. Min Act: -0.0001
Data Index: 919398 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.7035. Min Act: -0.0001
Data Index: 104510 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.7024. Min Act: -0.0001
Data Index: 1026655 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.6344. Min Act: -0.0001
Data Index: 385618 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.7626. Min Act: -0.0001
Data Index: 666968 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.7120. Min Act: -0.0001
Data Index: 796736 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.7340. Min Act: -0.0001
Data Index: 959601 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8361. Min Range: -0.8361
Max Act: 0.7637. Min Act: -0.0001
Data Index: 59097 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19