Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2087 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.7106. Min Act: -0.0001
Data Index: 1213656 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.7198. Min Act: -0.0001
Data Index: 254517 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.4716. Min Act: -0.0001
Data Index: 236450 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.4649. Min Act: -0.0001
Data Index: 1047668 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.4779. Min Act: -0.0001
Data Index: 967647 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.5053. Min Act: -0.0001
Data Index: 271451 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.3565. Min Act: -0.0001
Data Index: 235811 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.3954. Min Act: -0.0001
Data Index: 675402 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.3632. Min Act: -0.0001
Data Index: 1272460 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.3990. Min Act: -0.0001
Data Index: 604161 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.4436. Min Act: -0.0001
Data Index: 230542 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.2457. Min Act: -0.0001
Data Index: 1604662 (Python Code)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.2630. Min Act: -0.0001
Data Index: 189589 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.2558. Min Act: -0.0001
Data Index: 1345749 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.2402. Min Act: -0.0001
Data Index: 816241 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.2047. Min Act: -0.0001
Data Index: 1443915 (Python Code)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.1923. Min Act: -0.0001
Data Index: 727382 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.1709. Min Act: -0.0001
Data Index: 295145 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.1456. Min Act: -0.0001
Data Index: 421323 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7198. Min Range: -1.7198
Max Act: 1.1848. Min Act: -0.0001
Data Index: 757445 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19