Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3195 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2572. Min Act: -0.0001
Data Index: 579893 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2585. Min Act: -0.0001
Data Index: 1309547 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2636. Min Act: -0.0001
Data Index: 206936 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2484. Min Act: -0.0001
Data Index: 649899 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2450. Min Act: -0.0001
Data Index: 24291 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2341. Min Act: -0.0001
Data Index: 17909 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2188. Min Act: -0.0001
Data Index: 569032 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2366. Min Act: -0.0001
Data Index: 865175 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2194. Min Act: -0.0001
Data Index: 1496502 (Python Code)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2326. Min Act: -0.0001
Data Index: 710903 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2184. Min Act: -0.0001
Data Index: 310094 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2340. Min Act: -0.0001
Data Index: 1168877 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2324. Min Act: -0.0001
Data Index: 135855 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2248. Min Act: -0.0001
Data Index: 1356365 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2158. Min Act: -0.0001
Data Index: 1357103 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.1637. Min Act: -0.0001
Data Index: 113788 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2238. Min Act: -0.0001
Data Index: 734372 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2299. Min Act: -0.0001
Data Index: 268933 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2302. Min Act: -0.0001
Data Index: 486967 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2636. Min Range: -0.2636
Max Act: 0.2065. Min Act: -0.0001
Data Index: 1514466 (Python Code)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19