Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4119 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.5959. Min Range: -3.5959
Max Act: 3.5959. Min Act: -0.0001
Data Index: 41657 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5959. Min Range: -3.5959
Max Act: 3.2515. Min Act: -0.0001
Data Index: 756390 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5959. Min Range: -3.5959
Max Act: 2.8796. Min Act: -0.0001
Data Index: 1306328 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5959. Min Range: -3.5959
Max Act: 2.9937. Min Act: -0.0001
Data Index: 1083461 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5959. Min Range: -3.5959
Max Act: 2.9360. Min Act: -0.0001
Data Index: 1211544 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5959. Min Range: -3.5959
Max Act: 3.3529. Min Act: -0.0001
Data Index: 893247 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5959. Min Range: -3.5959
Max Act: 2.8185. Min Act: -0.0001
Data Index: 670560 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5959. Min Range: -3.5959
Max Act: 2.6536. Min Act: -0.0001
Data Index: 327956 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5959. Min Range: -3.5959
Max Act: 2.6330. Min Act: -0.0001
Data Index: 1077381 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5959. Min Range: -3.5959
Max Act: 2.8616. Min Act: -0.0001
Data Index: 869680 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5959. Min Range: -3.5959
Max Act: 2.6858. Min Act: -0.0001
Data Index: 4036 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5959. Min Range: -3.5959
Max Act: 2.4973. Min Act: -0.0001
Data Index: 804882 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5959. Min Range: -3.5959
Max Act: 3.0228. Min Act: -0.0001
Data Index: 367313 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5959. Min Range: -3.5959
Max Act: 2.5986. Min Act: -0.0001
Data Index: 432825 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5959. Min Range: -3.5959
Max Act: 3.1252. Min Act: -0.0001
Data Index: 555477 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5959. Min Range: -3.5959
Max Act: 2.6921. Min Act: -0.0001
Data Index: 381958 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5959. Min Range: -3.5959
Max Act: 2.3091. Min Act: -0.0001
Data Index: 1237655 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5959. Min Range: -3.5959
Max Act: 2.2769. Min Act: -0.0001
Data Index: 1029095 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5959. Min Range: -3.5959
Max Act: 2.6451. Min Act: -0.0001
Data Index: 466606 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5959. Min Range: -3.5959
Max Act: 2.1528. Min Act: -0.0001
Data Index: 1291915 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19