Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2963 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.5837. Min Act: -0.0001
Data Index: 1356156 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.5243. Min Act: -0.0001
Data Index: 1064505 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.4800. Min Act: -0.0001
Data Index: 946249 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.4764. Min Act: -0.0001
Data Index: 972825 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.3546. Min Act: -0.0001
Data Index: 965801 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.4767. Min Act: -0.0001
Data Index: 554689 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.3660. Min Act: -0.0001
Data Index: 613538 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.3837. Min Act: -0.0001
Data Index: 207603 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.3825. Min Act: -0.0001
Data Index: 391165 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.3831. Min Act: -0.0001
Data Index: 468481 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.3705. Min Act: -0.0001
Data Index: 711211 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.3653. Min Act: -0.0001
Data Index: 1104974 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.3585. Min Act: -0.0001
Data Index: 996039 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.3878. Min Act: -0.0001
Data Index: 419122 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.2606. Min Act: -0.0001
Data Index: 587539 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.3118. Min Act: -0.0001
Data Index: 666891 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.2927. Min Act: -0.0001
Data Index: 1004315 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.2076. Min Act: -0.0001
Data Index: 396274 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.2384. Min Act: -0.0001
Data Index: 715643 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5837. Min Range: -1.5837
Max Act: 1.2991. Min Act: -0.0001
Data Index: 1176626 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19