Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 983 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.9788. Min Act: -0.0001
Data Index: 950732 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.8779. Min Act: -0.0001
Data Index: 539143 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.9994. Min Act: -0.0001
Data Index: 1135417 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.9301. Min Act: -0.0001
Data Index: 1146434 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.9743. Min Act: -0.0001
Data Index: 93238 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.8442. Min Act: -0.0001
Data Index: 378104 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.8862. Min Act: -0.0001
Data Index: 253218 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.8911. Min Act: -0.0002
Data Index: 1051160 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.8630. Min Act: -0.0001
Data Index: 616214 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.8586. Min Act: -0.0001
Data Index: 966614 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.8097. Min Act: -0.0001
Data Index: 1349910 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.8123. Min Act: -0.0001
Data Index: 481862 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.8506. Min Act: -0.0002
Data Index: 1269591 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.7435. Min Act: -0.0001
Data Index: 760597 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.8325. Min Act: -0.0001
Data Index: 682592 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.8552. Min Act: -0.0001
Data Index: 97905 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.7285. Min Act: -0.0001
Data Index: 794476 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.7675. Min Act: -0.0002
Data Index: 756080 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.7655. Min Act: -0.0001
Data Index: 744540 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9994. Min Range: -0.9994
Max Act: 0.7155. Min Act: -0.0002
Data Index: 1006137 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19