Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4054 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.6387. Min Act: -0.0001
Data Index: 514724 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.7781. Min Act: -0.0001
Data Index: 4711 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.6213. Min Act: -0.0001
Data Index: 469264 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.4890. Min Act: -0.0001
Data Index: 1232668 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.4840. Min Act: -0.0001
Data Index: 925720 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.8210. Min Act: -0.0001
Data Index: 444457 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.5321. Min Act: -0.0001
Data Index: 758762 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.4373. Min Act: -0.0001
Data Index: 184676 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.3940. Min Act: -0.0001
Data Index: 484867 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.3941. Min Act: -0.0001
Data Index: 238113 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.1469. Min Act: -0.0001
Data Index: 180015 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.3243. Min Act: -0.0001
Data Index: 494530 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.4398. Min Act: -0.0001
Data Index: 144642 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.4318. Min Act: -0.0001
Data Index: 1177296 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.2972. Min Act: -0.0001
Data Index: 1091623 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.3927. Min Act: -0.0001
Data Index: 672452 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.2896. Min Act: -0.0001
Data Index: 610069 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.3997. Min Act: -0.0001
Data Index: 961902 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.3985. Min Act: -0.0001
Data Index: 132188 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8210. Min Range: -2.8210
Max Act: 2.2712. Min Act: -0.0001
Data Index: 27571 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19