Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 12 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.4899. Min Act: -0.0001
Data Index: 1643021 (Python Code)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.4788. Min Act: -0.0001
Data Index: 1605446 (Python Code)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.4835. Min Act: -0.0001
Data Index: 1647986 (Python Code)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.5022. Min Act: -0.0001
Data Index: 1517204 (Python Code)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.4062. Min Act: -0.0001
Data Index: 1532286 (Python Code)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.3658. Min Act: -0.0001
Data Index: 1474067 (Python Code)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.4213. Min Act: -0.0001
Data Index: 1479714 (Python Code)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.3577. Min Act: -0.0001
Data Index: 1583098 (Python Code)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.3486. Min Act: -0.0001
Data Index: 1539622 (Python Code)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.3157. Min Act: -0.0001
Data Index: 1464852 (Python Code)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.3468. Min Act: -0.0001
Data Index: 1551999 (Python Code)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.3036. Min Act: -0.0001
Data Index: 1494834 (Python Code)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.3139. Min Act: -0.0001
Data Index: 1456603 (Python Code)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.3631. Min Act: -0.0001
Data Index: 1648575 (Python Code)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.3487. Min Act: -0.0001
Data Index: 1435585 (Python Code)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.3274. Min Act: -0.0001
Data Index: 1650002 (Python Code)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.2625. Min Act: -0.0001
Data Index: 1425476 (Python Code)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.3488. Min Act: -0.0001
Data Index: 1630628 (Python Code)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.3358. Min Act: -0.0001
Data Index: 1412698 (Python Code)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5022. Min Range: -0.5022
Max Act: 0.3275. Min Act: -0.0001
Data Index: 1585286 (Python Code)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19