Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3609 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.9953. Min Act: -0.0001
Data Index: 1026740 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.9696. Min Act: -0.0001
Data Index: 903445 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.9436. Min Act: -0.0002
Data Index: 1197158 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.9697. Min Act: -0.0001
Data Index: 661437 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.9008. Min Act: -0.0001
Data Index: 17417 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.9130. Min Act: -0.0001
Data Index: 273785 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.9899. Min Act: -0.0001
Data Index: 609105 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.8797. Min Act: -0.0001
Data Index: 1263520 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.9370. Min Act: -0.0002
Data Index: 49899 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.9586. Min Act: -0.0001
Data Index: 389324 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.8936. Min Act: -0.0001
Data Index: 998253 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.8954. Min Act: -0.0001
Data Index: 163228 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.8826. Min Act: -0.0001
Data Index: 725116 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.8664. Min Act: -0.0001
Data Index: 480314 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.8643. Min Act: -0.0002
Data Index: 618828 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.9019. Min Act: -0.0001
Data Index: 663692 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.8141. Min Act: -0.0001
Data Index: 413576 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.9306. Min Act: -0.0001
Data Index: 1316926 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.8795. Min Act: -0.0001
Data Index: 1335585 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9953. Min Range: -0.9953
Max Act: 0.8621. Min Act: -0.0001
Data Index: 466087 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19