Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2482 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.7933. Min Act: -0.0001
Data Index: 673427 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.7710. Min Act: -0.0001
Data Index: 107502 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.8280. Min Act: -0.0001
Data Index: 887281 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.8929. Min Act: -0.0001
Data Index: 1355257 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.7816. Min Act: -0.0001
Data Index: 778067 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.6882. Min Act: -0.0001
Data Index: 547829 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.6977. Min Act: -0.0001
Data Index: 94418 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.7012. Min Act: -0.0001
Data Index: 689322 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.7373. Min Act: -0.0001
Data Index: 500781 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.6119. Min Act: -0.0001
Data Index: 1034826 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.6499. Min Act: -0.0001
Data Index: 282137 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.4990. Min Act: -0.0001
Data Index: 721399 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.4848. Min Act: -0.0001
Data Index: 538668 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.5027. Min Act: -0.0001
Data Index: 228857 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.5026. Min Act: -0.0001
Data Index: 89807 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.4520. Min Act: -0.0001
Data Index: 71850 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.4912. Min Act: -0.0001
Data Index: 709038 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.4558. Min Act: -0.0001
Data Index: 887770 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.3775. Min Act: -0.0001
Data Index: 52286 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8929. Min Range: -1.8929
Max Act: 1.5763. Min Act: -0.0001
Data Index: 1169831 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19