Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3208 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.4227. Min Range: -4.4227
Max Act: 4.4227. Min Act: -0.0001
Data Index: 431543 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4227. Min Range: -4.4227
Max Act: 4.2670. Min Act: -0.0001
Data Index: 897532 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4227. Min Range: -4.4227
Max Act: 4.0798. Min Act: -0.0001
Data Index: 948653 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4227. Min Range: -4.4227
Max Act: 4.3080. Min Act: -0.0001
Data Index: 368788 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4227. Min Range: -4.4227
Max Act: 3.5167. Min Act: -0.0001
Data Index: 459082 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4227. Min Range: -4.4227
Max Act: 3.9649. Min Act: -0.0001
Data Index: 1110465 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4227. Min Range: -4.4227
Max Act: 3.8192. Min Act: -0.0001
Data Index: 605920 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4227. Min Range: -4.4227
Max Act: 3.5352. Min Act: -0.0001
Data Index: 1053934 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4227. Min Range: -4.4227
Max Act: 3.6376. Min Act: -0.0001
Data Index: 284609 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4227. Min Range: -4.4227
Max Act: 3.3751. Min Act: -0.0001
Data Index: 1163624 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4227. Min Range: -4.4227
Max Act: 3.2460. Min Act: -0.0001
Data Index: 453742 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4227. Min Range: -4.4227
Max Act: 2.9686. Min Act: -0.0001
Data Index: 531579 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4227. Min Range: -4.4227
Max Act: 2.7560. Min Act: -0.0001
Data Index: 1009528 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4227. Min Range: -4.4227
Max Act: 2.5736. Min Act: -0.0001
Data Index: 569505 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4227. Min Range: -4.4227
Max Act: 2.4837. Min Act: -0.0001
Data Index: 227162 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4227. Min Range: -4.4227
Max Act: 2.3434. Min Act: -0.0001
Data Index: 925228 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4227. Min Range: -4.4227
Max Act: 2.2108. Min Act: -0.0001
Data Index: 1113805 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4227. Min Range: -4.4227
Max Act: 2.2936. Min Act: -0.0001
Data Index: 249211 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4227. Min Range: -4.4227
Max Act: 2.2679. Min Act: -0.0001
Data Index: 824457 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4227. Min Range: -4.4227
Max Act: 1.9607. Min Act: -0.0001
Data Index: 1309430 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19