Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2030 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.9555. Min Range: -2.9555
Max Act: 2.9439. Min Act: -0.0001
Data Index: 511771 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9555. Min Range: -2.9555
Max Act: 2.8158. Min Act: -0.0001
Data Index: 506999 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9555. Min Range: -2.9555
Max Act: 2.8144. Min Act: -0.0001
Data Index: 984129 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9555. Min Range: -2.9555
Max Act: 2.5610. Min Act: -0.0001
Data Index: 877046 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9555. Min Range: -2.9555
Max Act: 2.5580. Min Act: -0.0001
Data Index: 1240106 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9555. Min Range: -2.9555
Max Act: 2.6723. Min Act: -0.0001
Data Index: 347973 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9555. Min Range: -2.9555
Max Act: 2.9555. Min Act: -0.0001
Data Index: 753166 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9555. Min Range: -2.9555
Max Act: 2.4515. Min Act: -0.0001
Data Index: 876256 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9555. Min Range: -2.9555
Max Act: 2.5714. Min Act: -0.0001
Data Index: 441986 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9555. Min Range: -2.9555
Max Act: 2.6729. Min Act: -0.0001
Data Index: 735161 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9555. Min Range: -2.9555
Max Act: 2.5938. Min Act: -0.0001
Data Index: 1426393 (Python Code)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9555. Min Range: -2.9555
Max Act: 2.1271. Min Act: -0.0001
Data Index: 964631 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9555. Min Range: -2.9555
Max Act: 2.0682. Min Act: -0.0001
Data Index: 706090 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9555. Min Range: -2.9555
Max Act: 1.7865. Min Act: -0.0001
Data Index: 936938 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9555. Min Range: -2.9555
Max Act: 1.8523. Min Act: -0.0001
Data Index: 1211805 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9555. Min Range: -2.9555
Max Act: 1.9590. Min Act: -0.0001
Data Index: 756282 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9555. Min Range: -2.9555
Max Act: 1.9389. Min Act: -0.0001
Data Index: 1577297 (Python Code)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9555. Min Range: -2.9555
Max Act: 1.8299. Min Act: -0.0001
Data Index: 1010518 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9555. Min Range: -2.9555
Max Act: 1.8957. Min Act: -0.0001
Data Index: 526363 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9555. Min Range: -2.9555
Max Act: 1.8547. Min Act: -0.0001
Data Index: 283164 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19