Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2118 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.3902. Min Range: -3.3902
Max Act: 3.3902. Min Act: -0.0001
Data Index: 412373 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3902. Min Range: -3.3902
Max Act: 3.1732. Min Act: -0.0001
Data Index: 524060 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.9171. Min Act: -0.0001
Data Index: 424192 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.7738. Min Act: -0.0001
Data Index: 1173870 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.7496. Min Act: -0.0001
Data Index: 1179410 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.8438. Min Act: -0.0001
Data Index: 941120 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.8267. Min Act: -0.0001
Data Index: 742346 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.5990. Min Act: -0.0001
Data Index: 1235403 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.5755. Min Act: -0.0001
Data Index: 1254975 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.8117. Min Act: -0.0001
Data Index: 1195072 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.6028. Min Act: -0.0001
Data Index: 474029 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.5967. Min Act: -0.0001
Data Index: 403419 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.7105. Min Act: -0.0001
Data Index: 87230 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.5172. Min Act: -0.0001
Data Index: 364587 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.7357. Min Act: -0.0001
Data Index: 1220221 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.4527. Min Act: -0.0001
Data Index: 768560 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.3050. Min Act: -0.0001
Data Index: 926108 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.4171. Min Act: -0.0001
Data Index: 681870 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.3936. Min Act: -0.0001
Data Index: 169809 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3902. Min Range: -3.3902
Max Act: 2.3859. Min Act: -0.0001
Data Index: 1065161 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19