Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3762 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.3328. Min Range: -2.3328
Max Act: 2.2875. Min Act: -0.0001
Data Index: 904581 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3328. Min Range: -2.3328
Max Act: 2.1558. Min Act: -0.0001
Data Index: 236194 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3328. Min Range: -2.3328
Max Act: 2.1519. Min Act: -0.0001
Data Index: 645953 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3328. Min Range: -2.3328
Max Act: 2.3328. Min Act: -0.0001
Data Index: 479793 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3328. Min Range: -2.3328
Max Act: 1.9019. Min Act: -0.0001
Data Index: 803044 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3328. Min Range: -2.3328
Max Act: 2.1879. Min Act: -0.0001
Data Index: 24277 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3328. Min Range: -2.3328
Max Act: 1.9114. Min Act: -0.0001
Data Index: 859995 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3328. Min Range: -2.3328
Max Act: 1.9706. Min Act: -0.0001
Data Index: 709320 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3328. Min Range: -2.3328
Max Act: 1.8205. Min Act: -0.0001
Data Index: 488357 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3328. Min Range: -2.3328
Max Act: 1.7679. Min Act: -0.0001
Data Index: 4765 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3328. Min Range: -2.3328
Max Act: 1.6760. Min Act: -0.0001
Data Index: 1046472 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3328. Min Range: -2.3328
Max Act: 1.8541. Min Act: -0.0001
Data Index: 351415 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3328. Min Range: -2.3328
Max Act: 1.9547. Min Act: -0.0001
Data Index: 496430 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3328. Min Range: -2.3328
Max Act: 1.8931. Min Act: -0.0001
Data Index: 228532 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3328. Min Range: -2.3328
Max Act: 1.7795. Min Act: -0.0001
Data Index: 90164 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3328. Min Range: -2.3328
Max Act: 1.7506. Min Act: -0.0001
Data Index: 1244700 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3328. Min Range: -2.3328
Max Act: 1.6228. Min Act: -0.0001
Data Index: 661038 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3328. Min Range: -2.3328
Max Act: 1.6376. Min Act: -0.0001
Data Index: 44827 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3328. Min Range: -2.3328
Max Act: 1.5375. Min Act: -0.0001
Data Index: 512308 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3328. Min Range: -2.3328
Max Act: 1.7069. Min Act: -0.0001
Data Index: 1214667 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19