Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3326 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.8869. Min Act: -0.0001
Data Index: 1075055 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.8123. Min Act: -0.0001
Data Index: 483775 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.7832. Min Act: -0.0001
Data Index: 572828 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.7467. Min Act: -0.0001
Data Index: 1214090 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.8197. Min Act: -0.0001
Data Index: 951891 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.6608. Min Act: -0.0001
Data Index: 1263460 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.8494. Min Act: -0.0000
Data Index: 1305915 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.5436. Min Act: -0.0001
Data Index: 967958 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.4991. Min Act: -0.0000
Data Index: 1404823 (Python Code)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.5198. Min Act: -0.0000
Data Index: 343519 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.3647. Min Act: -0.0000
Data Index: 401778 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.4861. Min Act: -0.0001
Data Index: 500922 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.4528. Min Act: -0.0000
Data Index: 711767 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.4704. Min Act: -0.0000
Data Index: 1266708 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.4550. Min Act: -0.0000
Data Index: 975030 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.2978. Min Act: -0.0000
Data Index: 397461 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.4245. Min Act: -0.0000
Data Index: 931533 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.3384. Min Act: -0.0001
Data Index: 1043595 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.5337. Min Act: -0.0000
Data Index: 1217314 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8869. Min Range: -2.8869
Max Act: 2.2985. Min Act: -0.0001
Data Index: 128240 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19