Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2710 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.3303. Min Range: -3.3303
Max Act: 3.3303. Min Act: -0.0001
Data Index: 279788 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.9559. Min Act: -0.0000
Data Index: 404012 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.8636. Min Act: -0.0000
Data Index: 295942 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.7585. Min Act: -0.0001
Data Index: 690385 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.7659. Min Act: -0.0001
Data Index: 1254874 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.8443. Min Act: -0.0001
Data Index: 72196 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.6967. Min Act: -0.0001
Data Index: 645615 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.4974. Min Act: -0.0001
Data Index: 528572 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.7444. Min Act: -0.0001
Data Index: 30030 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.4561. Min Act: -0.0001
Data Index: 163935 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.5898. Min Act: -0.0001
Data Index: 106723 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.4751. Min Act: -0.0001
Data Index: 1273962 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.4432. Min Act: -0.0001
Data Index: 130099 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.2921. Min Act: -0.0001
Data Index: 992865 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.4404. Min Act: -0.0001
Data Index: 703776 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.4219. Min Act: -0.0001
Data Index: 685029 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.5120. Min Act: -0.0001
Data Index: 1354861 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.4968. Min Act: -0.0001
Data Index: 1046063 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.5039. Min Act: -0.0001
Data Index: 1358176 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3303. Min Range: -3.3303
Max Act: 2.5853. Min Act: -0.0001
Data Index: 92533 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19