Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2873 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.3086. Min Range: -2.3086
Max Act: 2.3086. Min Act: -0.0001
Data Index: 91265 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3086. Min Range: -2.3086
Max Act: 2.1794. Min Act: -0.0001
Data Index: 1421574 (Python Code)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.6842. Min Act: -0.0001
Data Index: 1287322 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.6731. Min Act: -0.0001
Data Index: 1537865 (Python Code)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.6916. Min Act: -0.0001
Data Index: 382968 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.7524. Min Act: -0.0001
Data Index: 1017678 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.6750. Min Act: -0.0001
Data Index: 1452586 (Python Code)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.5324. Min Act: -0.0001
Data Index: 1592004 (Python Code)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.4390. Min Act: -0.0001
Data Index: 1602065 (Python Code)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.4295. Min Act: -0.0001
Data Index: 181350 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.5117. Min Act: -0.0001
Data Index: 801320 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.5554. Min Act: -0.0001
Data Index: 1449146 (Python Code)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.5328. Min Act: -0.0001
Data Index: 615709 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.5220. Min Act: -0.0001
Data Index: 1392761 (Python Code)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.3654. Min Act: -0.0001
Data Index: 1417772 (Python Code)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.4288. Min Act: -0.0001
Data Index: 1574387 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.3775. Min Act: -0.0001
Data Index: 1086687 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.4143. Min Act: -0.0001
Data Index: 972027 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.4071. Min Act: -0.0001
Data Index: 713897 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3086. Min Range: -2.3086
Max Act: 1.3585. Min Act: -0.0001
Data Index: 1432336 (Python Code)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19