Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2754 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4594. Min Act: -0.0001
Data Index: 727831 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4859. Min Act: -0.0001
Data Index: 715142 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4300. Min Act: -0.0001
Data Index: 170245 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.3342. Min Act: -0.0001
Data Index: 329946 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.3372. Min Act: -0.0001
Data Index: 1332195 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.3322. Min Act: -0.0001
Data Index: 455404 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.3284. Min Act: -0.0001
Data Index: 1505831 (Python Code)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.3235. Min Act: -0.0001
Data Index: 1018011 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.3179. Min Act: -0.0001
Data Index: 616572 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.3004. Min Act: -0.0001
Data Index: 426225 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.2868. Min Act: -0.0001
Data Index: 1509057 (Python Code)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.2950. Min Act: -0.0001
Data Index: 1311096 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.2909. Min Act: -0.0001
Data Index: 180552 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.3074. Min Act: -0.0001
Data Index: 605227 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.2878. Min Act: -0.0001
Data Index: 1147820 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.2974. Min Act: -0.0001
Data Index: 348040 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.2849. Min Act: -0.0001
Data Index: 969242 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.2846. Min Act: -0.0001
Data Index: 1070111 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.2550. Min Act: -0.0001
Data Index: 828084 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.2797. Min Act: -0.0001
Data Index: 1038139 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19