Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4577 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.1175. Min Act: -0.0001
Data Index: 105640 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.1123. Min Act: -0.0001
Data Index: 328334 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.1124. Min Act: -0.0002
Data Index: 1344031 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.1139. Min Act: -0.0001
Data Index: 210878 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.1002. Min Act: -0.0001
Data Index: 634927 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0933. Min Act: -0.0001
Data Index: 1228479 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0964. Min Act: -0.0001
Data Index: 838165 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0921. Min Act: -0.0001
Data Index: 338846 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0920. Min Act: -0.0001
Data Index: 490769 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0914. Min Act: -0.0001
Data Index: 1104579 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0886. Min Act: -0.0001
Data Index: 438281 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0889. Min Act: -0.0001
Data Index: 480378 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0891. Min Act: -0.0001
Data Index: 1219622 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0891. Min Act: -0.0001
Data Index: 254319 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0906. Min Act: -0.0001
Data Index: 672204 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0862. Min Act: -0.0001
Data Index: 584198 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0858. Min Act: -0.0001
Data Index: 1205780 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0854. Min Act: -0.0001
Data Index: 32515 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0882. Min Act: -0.0001
Data Index: 59942 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0829. Min Act: -0.0001
Data Index: 1157388 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19