Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2567 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.6930. Min Act: -0.0001
Data Index: 816786 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.5603. Min Act: -0.0001
Data Index: 777769 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.5434. Min Act: -0.0001
Data Index: 462730 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.5050. Min Act: -0.0001
Data Index: 806357 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.4869. Min Act: -0.0001
Data Index: 1273866 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.4989. Min Act: -0.0001
Data Index: 1076281 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.5102. Min Act: -0.0001
Data Index: 1356620 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.4711. Min Act: -0.0001
Data Index: 440975 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.5006. Min Act: -0.0001
Data Index: 990827 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.4659. Min Act: -0.0001
Data Index: 312006 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.4479. Min Act: -0.0001
Data Index: 1334704 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.4132. Min Act: -0.0001
Data Index: 221022 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.4703. Min Act: -0.0001
Data Index: 793613 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.4723. Min Act: -0.0001
Data Index: 920876 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.4831. Min Act: -0.0001
Data Index: 1408334 (Python Code)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.4269. Min Act: -0.0001
Data Index: 1222376 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.4598. Min Act: -0.0001
Data Index: 1529510 (Python Code)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.4738. Min Act: -0.0001
Data Index: 768978 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.4573. Min Act: -0.0001
Data Index: 14774 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6930. Min Range: -0.6930
Max Act: 0.5039. Min Act: -0.0001
Data Index: 140845 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19