Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2205 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.7915. Min Act: -0.0001
Data Index: 1184725 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.7656. Min Act: -0.0001
Data Index: 483447 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.6550. Min Act: -0.0001
Data Index: 1121269 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.7432. Min Act: -0.0001
Data Index: 1284997 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.6245. Min Act: -0.0001
Data Index: 1132713 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.6744. Min Act: -0.0001
Data Index: 786402 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.5584. Min Act: -0.0001
Data Index: 1012913 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.6381. Min Act: -0.0001
Data Index: 1079172 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.5953. Min Act: -0.0001
Data Index: 612078 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.5949. Min Act: -0.0001
Data Index: 278546 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.5339. Min Act: -0.0001
Data Index: 946770 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.4609. Min Act: -0.0001
Data Index: 475172 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.5003. Min Act: -0.0001
Data Index: 1183959 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.4923. Min Act: -0.0001
Data Index: 640439 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.5271. Min Act: -0.0001
Data Index: 940121 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.5685. Min Act: -0.0001
Data Index: 1243927 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.4848. Min Act: -0.0001
Data Index: 255571 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.3976. Min Act: -0.0001
Data Index: 705694 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.4353. Min Act: -0.0001
Data Index: 1207922 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7915. Min Range: -1.7915
Max Act: 1.3815. Min Act: -0.0001
Data Index: 1008030 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19