Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 895 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.2138. Min Range: -1.2138
Max Act: 1.2138. Min Act: -0.0001
Data Index: 130478 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2138. Min Range: -1.2138
Max Act: 1.1025. Min Act: -0.0001
Data Index: 1336757 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2138. Min Range: -1.2138
Max Act: 1.1214. Min Act: -0.0001
Data Index: 250838 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2138. Min Range: -1.2138
Max Act: 1.0773. Min Act: -0.0001
Data Index: 404746 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2138. Min Range: -1.2138
Max Act: 1.0724. Min Act: -0.0001
Data Index: 1108190 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2138. Min Range: -1.2138
Max Act: 0.9918. Min Act: -0.0001
Data Index: 222280 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2138. Min Range: -1.2138
Max Act: 0.9737. Min Act: -0.0001
Data Index: 1351114 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2138. Min Range: -1.2138
Max Act: 0.9389. Min Act: -0.0001
Data Index: 339403 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2138. Min Range: -1.2138
Max Act: 0.9715. Min Act: -0.0001
Data Index: 943572 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2138. Min Range: -1.2138
Max Act: 0.9204. Min Act: -0.0001
Data Index: 699586 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2138. Min Range: -1.2138
Max Act: 0.9577. Min Act: -0.0001
Data Index: 730801 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2138. Min Range: -1.2138
Max Act: 0.8961. Min Act: -0.0001
Data Index: 149421 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2138. Min Range: -1.2138
Max Act: 0.9078. Min Act: -0.0001
Data Index: 452980 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2138. Min Range: -1.2138
Max Act: 0.8983. Min Act: -0.0001
Data Index: 394905 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2138. Min Range: -1.2138
Max Act: 0.9404. Min Act: -0.0001
Data Index: 727938 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2138. Min Range: -1.2138
Max Act: 0.8739. Min Act: -0.0001
Data Index: 676056 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2138. Min Range: -1.2138
Max Act: 0.8710. Min Act: -0.0001
Data Index: 1336501 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2138. Min Range: -1.2138
Max Act: 0.8901. Min Act: -0.0001
Data Index: 235860 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2138. Min Range: -1.2138
Max Act: 0.9206. Min Act: -0.0001
Data Index: 578304 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2138. Min Range: -1.2138
Max Act: 0.8570. Min Act: -0.0001
Data Index: 407836 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19