Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4344 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.1665. Min Range: -1.1665
Max Act: 1.1665. Min Act: -0.0001
Data Index: 393317 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.9273. Min Act: -0.0001
Data Index: 639621 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.8013. Min Act: -0.0001
Data Index: 234547 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.8506. Min Act: -0.0001
Data Index: 916321 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.8745. Min Act: -0.0001
Data Index: 1490184 (Python Code)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.7325. Min Act: -0.0001
Data Index: 1385975 (Python Code)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.8456. Min Act: -0.0001
Data Index: 100093 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.7589. Min Act: -0.0001
Data Index: 1073651 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.7557. Min Act: -0.0002
Data Index: 1227932 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.7787. Min Act: -0.0001
Data Index: 124408 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.7255. Min Act: -0.0001
Data Index: 115918 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.8227. Min Act: -0.0001
Data Index: 454633 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.7919. Min Act: -0.0001
Data Index: 184408 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.7603. Min Act: -0.0001
Data Index: 1159454 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.7518. Min Act: -0.0001
Data Index: 443461 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.7943. Min Act: -0.0001
Data Index: 686760 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.7588. Min Act: -0.0001
Data Index: 848293 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.7979. Min Act: -0.0001
Data Index: 364433 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.7544. Min Act: -0.0001
Data Index: 1357138 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1665. Min Range: -1.1665
Max Act: 0.7182. Min Act: -0.0001
Data Index: 216082 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19