Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1680 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.6033. Min Act: -0.0001
Data Index: 982606 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.4762. Min Act: -0.0001
Data Index: 521397 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.3392. Min Act: -0.0001
Data Index: 56916 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.3508. Min Act: -0.0001
Data Index: 1195141 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.3587. Min Act: -0.0001
Data Index: 106875 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.3767. Min Act: -0.0001
Data Index: 126638 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.2244. Min Act: -0.0001
Data Index: 607046 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.2182. Min Act: -0.0001
Data Index: 934537 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.1919. Min Act: -0.0001
Data Index: 1043342 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.2529. Min Act: -0.0001
Data Index: 439946 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.1658. Min Act: -0.0001
Data Index: 189236 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.1804. Min Act: -0.0001
Data Index: 511001 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.1613. Min Act: -0.0001
Data Index: 1295993 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.1081. Min Act: -0.0001
Data Index: 654653 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.1372. Min Act: -0.0001
Data Index: 104189 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.0505. Min Act: -0.0001
Data Index: 546622 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.1139. Min Act: -0.0001
Data Index: 560693 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.0331. Min Act: -0.0001
Data Index: 613170 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6033. Min Range: -1.6033
Max Act: 0.9528. Min Act: -0.0001
Data Index: 1031521 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6033. Min Range: -1.6033
Max Act: 1.0174. Min Act: -0.0001
Data Index: 1085375 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19