Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3241 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.3695. Min Act: -0.0001
Data Index: 113361 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.3998. Min Act: -0.0001
Data Index: 1435395 (Python Code)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.3424. Min Act: -0.0001
Data Index: 545267 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.3281. Min Act: -0.0001
Data Index: 1401580 (Python Code)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.3179. Min Act: -0.0001
Data Index: 196967 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.3041. Min Act: -0.0001
Data Index: 1396209 (Python Code)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.3193. Min Act: -0.0001
Data Index: 1625938 (Python Code)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.2935. Min Act: -0.0001
Data Index: 1406095 (Python Code)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.3564. Min Act: -0.0001
Data Index: 1074845 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.2916. Min Act: -0.0001
Data Index: 536884 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.3025. Min Act: -0.0001
Data Index: 504107 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.3233. Min Act: -0.0001
Data Index: 39194 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.2896. Min Act: -0.0001
Data Index: 1539595 (Python Code)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.3103. Min Act: -0.0001
Data Index: 1332461 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.2987. Min Act: -0.0001
Data Index: 1295826 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.2814. Min Act: -0.0001
Data Index: 1383612 (Python Code)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.2903. Min Act: -0.0001
Data Index: 35469 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.2786. Min Act: -0.0001
Data Index: 820045 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.2867. Min Act: -0.0001
Data Index: 1296992 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3998. Min Range: -0.3998
Max Act: 0.2593. Min Act: -0.0001
Data Index: 286301 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19