Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2779 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.2098. Min Range: -4.2098
Max Act: 4.2098. Min Act: -0.0001
Data Index: 863766 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2098. Min Range: -4.2098
Max Act: 3.6421. Min Act: -0.0001
Data Index: 1311934 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2098. Min Range: -4.2098
Max Act: 3.1658. Min Act: -0.0001
Data Index: 764702 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2098. Min Range: -4.2098
Max Act: 3.4017. Min Act: -0.0001
Data Index: 1250136 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2098. Min Range: -4.2098
Max Act: 3.1258. Min Act: -0.0001
Data Index: 827290 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2098. Min Range: -4.2098
Max Act: 3.2518. Min Act: -0.0001
Data Index: 1099575 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2098. Min Range: -4.2098
Max Act: 2.8701. Min Act: -0.0001
Data Index: 440718 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2098. Min Range: -4.2098
Max Act: 2.4796. Min Act: -0.0001
Data Index: 608956 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2098. Min Range: -4.2098
Max Act: 2.3794. Min Act: -0.0001
Data Index: 542644 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2098. Min Range: -4.2098
Max Act: 2.2883. Min Act: -0.0001
Data Index: 339884 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2098. Min Range: -4.2098
Max Act: 2.2099. Min Act: -0.0001
Data Index: 69045 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2098. Min Range: -4.2098
Max Act: 1.6763. Min Act: -0.0001
Data Index: 605208 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2098. Min Range: -4.2098
Max Act: 1.8783. Min Act: -0.0001
Data Index: 447847 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2098. Min Range: -4.2098
Max Act: 2.1990. Min Act: -0.0001
Data Index: 515571 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2098. Min Range: -4.2098
Max Act: 1.8974. Min Act: -0.0001
Data Index: 338115 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2098. Min Range: -4.2098
Max Act: 1.7447. Min Act: -0.0001
Data Index: 468882 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2098. Min Range: -4.2098
Max Act: 1.9394. Min Act: -0.0001
Data Index: 738406 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2098. Min Range: -4.2098
Max Act: 1.9354. Min Act: -0.0001
Data Index: 350896 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2098. Min Range: -4.2098
Max Act: 1.7030. Min Act: -0.0001
Data Index: 117797 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2098. Min Range: -4.2098
Max Act: 1.5595. Min Act: -0.0001
Data Index: 1201537 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19