Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2976 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.7171. Min Act: -0.0001
Data Index: 471391 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.4549. Min Act: -0.0001
Data Index: 169367 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.4215. Min Act: -0.0001
Data Index: 9243 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.3503. Min Act: -0.0001
Data Index: 444872 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.4747. Min Act: -0.0001
Data Index: 632793 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.3620. Min Act: -0.0001
Data Index: 1033371 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.5001. Min Act: -0.0001
Data Index: 537147 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.2257. Min Act: -0.0001
Data Index: 1121921 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.2438. Min Act: -0.0001
Data Index: 446273 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.2013. Min Act: -0.0001
Data Index: 812532 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.1925. Min Act: -0.0001
Data Index: 972684 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.3214. Min Act: -0.0001
Data Index: 1225276 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.2838. Min Act: -0.0001
Data Index: 214211 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.2778. Min Act: -0.0001
Data Index: 1047094 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.1877. Min Act: -0.0001
Data Index: 1128598 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.2310. Min Act: -0.0001
Data Index: 382062 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.0461. Min Act: -0.0001
Data Index: 1066865 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.0172. Min Act: -0.0001
Data Index: 981873 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.3543. Min Act: -0.0001
Data Index: 696821 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7171. Min Range: -2.7171
Max Act: 2.2271. Min Act: -0.0001
Data Index: 95051 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19