Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2761 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.7676. Min Range: -2.7676
Max Act: 2.7676. Min Act: -0.0000
Data Index: 71628 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7676. Min Range: -2.7676
Max Act: 1.6722. Min Act: -0.0000
Data Index: 596356 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7676. Min Range: -2.7676
Max Act: 1.7255. Min Act: -0.0000
Data Index: 1209332 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7676. Min Range: -2.7676
Max Act: 1.4493. Min Act: -0.0000
Data Index: 1298243 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7676. Min Range: -2.7676
Max Act: 1.2172. Min Act: -0.0000
Data Index: 1180864 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7676. Min Range: -2.7676
Max Act: 1.1425. Min Act: -0.0000
Data Index: 567796 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7676. Min Range: -2.7676
Max Act: 0.9756. Min Act: -0.0000
Data Index: 1113489 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7676. Min Range: -2.7676
Max Act: 0.9554. Min Act: -0.0000
Data Index: 1124633 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7676. Min Range: -2.7676
Max Act: 0.9561. Min Act: -0.0000
Data Index: 250647 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7676. Min Range: -2.7676
Max Act: 0.9238. Min Act: -0.0000
Data Index: 877490 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7676. Min Range: -2.7676
Max Act: 0.9330. Min Act: -0.0000
Data Index: 1139236 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7676. Min Range: -2.7676
Max Act: 0.9073. Min Act: -0.0000
Data Index: 455911 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7676. Min Range: -2.7676
Max Act: 0.9128. Min Act: -0.0000
Data Index: 656145 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7676. Min Range: -2.7676
Max Act: 0.9098. Min Act: -0.0000
Data Index: 159762 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7676. Min Range: -2.7676
Max Act: 0.8945. Min Act: -0.0000
Data Index: 413826 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7676. Min Range: -2.7676
Max Act: 0.9221. Min Act: -0.0000
Data Index: 161758 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7676. Min Range: -2.7676
Max Act: 0.9483. Min Act: -0.0000
Data Index: 1338392 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7676. Min Range: -2.7676
Max Act: 0.8609. Min Act: -0.0000
Data Index: 574383 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7676. Min Range: -2.7676
Max Act: 0.8322. Min Act: -0.0000
Data Index: 242708 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7676. Min Range: -2.7676
Max Act: 0.8191. Min Act: -0.0000
Data Index: 527122 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19