Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2888 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.8832. Min Range: -3.8832
Max Act: 3.8832. Min Act: -0.0001
Data Index: 367463 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8832. Min Range: -3.8832
Max Act: 3.7193. Min Act: -0.0001
Data Index: 553645 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8832. Min Range: -3.8832
Max Act: 3.1064. Min Act: -0.0001
Data Index: 1646338 (Python Code)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.9952. Min Act: -0.0001
Data Index: 148039 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.7103. Min Act: -0.0001
Data Index: 729626 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.8375. Min Act: -0.0001
Data Index: 1515110 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.4740. Min Act: -0.0001
Data Index: 1561299 (Python Code)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.7115. Min Act: -0.0001
Data Index: 1335637 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.4468. Min Act: -0.0001
Data Index: 1616059 (Python Code)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.6239. Min Act: -0.0001
Data Index: 1405201 (Python Code)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.4928. Min Act: -0.0001
Data Index: 184197 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.2312. Min Act: -0.0001
Data Index: 1365601 (Python Code)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.3887. Min Act: -0.0001
Data Index: 1570119 (Python Code)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.3303. Min Act: -0.0001
Data Index: 469538 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.3414. Min Act: -0.0001
Data Index: 1367969 (Python Code)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.2658. Min Act: -0.0001
Data Index: 1387006 (Python Code)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.5217. Min Act: -0.0001
Data Index: 992979 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.5293. Min Act: -0.0001
Data Index: 1508480 (Python Code)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.3927. Min Act: -0.0001
Data Index: 1459705 (Python Code)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8832. Min Range: -3.8832
Max Act: 2.4644. Min Act: -0.0001
Data Index: 1381449 (Python Code)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19