Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1339 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.2077. Min Range: -3.2077
Max Act: 3.1818. Min Act: -0.0001
Data Index: 816666 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2077. Min Range: -3.2077
Max Act: 3.2077. Min Act: -0.0001
Data Index: 728753 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2077. Min Range: -3.2077
Max Act: 3.0220. Min Act: -0.0001
Data Index: 900389 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.7135. Min Act: -0.0001
Data Index: 823969 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.6974. Min Act: -0.0001
Data Index: 1179422 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.5663. Min Act: -0.0001
Data Index: 220998 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.3533. Min Act: -0.0001
Data Index: 622147 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.4888. Min Act: -0.0001
Data Index: 417070 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.2846. Min Act: -0.0001
Data Index: 1205457 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.3648. Min Act: -0.0001
Data Index: 1121587 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.2960. Min Act: -0.0001
Data Index: 308681 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.2784. Min Act: -0.0001
Data Index: 259678 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.5150. Min Act: -0.0001
Data Index: 457712 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.2849. Min Act: -0.0001
Data Index: 886288 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.2292. Min Act: -0.0001
Data Index: 634055 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.3215. Min Act: -0.0001
Data Index: 965187 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.0670. Min Act: -0.0001
Data Index: 718739 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.0306. Min Act: -0.0001
Data Index: 487227 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.0207. Min Act: -0.0001
Data Index: 536609 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2077. Min Range: -3.2077
Max Act: 2.0942. Min Act: -0.0001
Data Index: 541984 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19