Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1997 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.8195. Min Act: -0.0001
Data Index: 438325 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.8124. Min Act: -0.0001
Data Index: 25499 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.8096. Min Act: -0.0001
Data Index: 1198538 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.7724. Min Act: -0.0001
Data Index: 278071 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.7589. Min Act: -0.0001
Data Index: 62526 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.6972. Min Act: -0.0001
Data Index: 1182903 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.6786. Min Act: -0.0001
Data Index: 988536 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.6763. Min Act: -0.0001
Data Index: 929230 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.6849. Min Act: -0.0001
Data Index: 1345974 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.6720. Min Act: -0.0001
Data Index: 419247 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.6959. Min Act: -0.0001
Data Index: 47339 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.6908. Min Act: -0.0001
Data Index: 131406 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.6933. Min Act: -0.0001
Data Index: 358946 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.6908. Min Act: -0.0001
Data Index: 471381 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.6642. Min Act: -0.0001
Data Index: 85712 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.6246. Min Act: -0.0001
Data Index: 1095661 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.6551. Min Act: -0.0001
Data Index: 938076 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.6378. Min Act: -0.0001
Data Index: 1133835 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.6952. Min Act: -0.0001
Data Index: 863161 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8195. Min Range: -0.8195
Max Act: 0.6074. Min Act: -0.0001
Data Index: 969298 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19