Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2171 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.2105. Min Range: -3.2105
Max Act: 3.2105. Min Act: -0.0001
Data Index: 467667 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.9026. Min Act: -0.0001
Data Index: 179033 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.5831. Min Act: -0.0001
Data Index: 896401 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.4956. Min Act: -0.0001
Data Index: 446195 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.5368. Min Act: -0.0001
Data Index: 1289549 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.3501. Min Act: -0.0001
Data Index: 350635 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.3930. Min Act: -0.0001
Data Index: 1031393 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.4474. Min Act: -0.0001
Data Index: 949647 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.3714. Min Act: -0.0001
Data Index: 1082658 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.2245. Min Act: -0.0001
Data Index: 369749 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.1013. Min Act: -0.0001
Data Index: 983611 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.1643. Min Act: -0.0001
Data Index: 650222 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.1743. Min Act: -0.0001
Data Index: 508959 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.1058. Min Act: -0.0001
Data Index: 502069 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.0574. Min Act: -0.0001
Data Index: 909785 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.0701. Min Act: -0.0001
Data Index: 1120523 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.1142. Min Act: -0.0001
Data Index: 1350722 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.0907. Min Act: -0.0001
Data Index: 1300306 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2105. Min Range: -3.2105
Max Act: 1.9722. Min Act: -0.0001
Data Index: 213066 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2105. Min Range: -3.2105
Max Act: 2.0304. Min Act: -0.0001
Data Index: 445040 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19