Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1886 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.4852. Min Range: -2.4852
Max Act: 2.4793. Min Act: -0.0001
Data Index: 953416 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4852. Min Range: -2.4852
Max Act: 2.4852. Min Act: -0.0001
Data Index: 518328 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4852. Min Range: -2.4852
Max Act: 2.1217. Min Act: -0.0001
Data Index: 983974 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.9802. Min Act: -0.0001
Data Index: 235187 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.8187. Min Act: -0.0001
Data Index: 75513 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.7922. Min Act: -0.0001
Data Index: 887949 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.7952. Min Act: -0.0001
Data Index: 337541 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.7819. Min Act: -0.0001
Data Index: 538378 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.5739. Min Act: -0.0001
Data Index: 997466 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.7417. Min Act: -0.0001
Data Index: 29666 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.7313. Min Act: -0.0001
Data Index: 701011 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.8465. Min Act: -0.0001
Data Index: 1223894 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.7262. Min Act: -0.0001
Data Index: 471100 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.9256. Min Act: -0.0001
Data Index: 1223324 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.6047. Min Act: -0.0001
Data Index: 1283600 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.6004. Min Act: -0.0001
Data Index: 4528 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.8768. Min Act: -0.0001
Data Index: 433852 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.6640. Min Act: -0.0001
Data Index: 1483930 (Python Code)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.6452. Min Act: -0.0001
Data Index: 1495235 (Python Code)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4852. Min Range: -2.4852
Max Act: 1.5387. Min Act: -0.0001
Data Index: 1212579 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19