Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3170 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.7561. Min Range: -4.7561
Max Act: 4.7561. Min Act: -0.0001
Data Index: 900226 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7561. Min Range: -4.7561
Max Act: 4.5280. Min Act: -0.0001
Data Index: 360632 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7561. Min Range: -4.7561
Max Act: 4.4626. Min Act: -0.0001
Data Index: 830836 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7561. Min Range: -4.7561
Max Act: 4.3488. Min Act: -0.0001
Data Index: 324278 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7561. Min Range: -4.7561
Max Act: 4.3583. Min Act: -0.0001
Data Index: 1235768 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7561. Min Range: -4.7561
Max Act: 4.1347. Min Act: -0.0001
Data Index: 1110195 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7561. Min Range: -4.7561
Max Act: 4.2000. Min Act: -0.0001
Data Index: 202423 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7561. Min Range: -4.7561
Max Act: 3.9044. Min Act: -0.0001
Data Index: 1199291 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7561. Min Range: -4.7561
Max Act: 3.6240. Min Act: -0.0001
Data Index: 1059948 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7561. Min Range: -4.7561
Max Act: 3.6286. Min Act: -0.0001
Data Index: 615903 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7561. Min Range: -4.7561
Max Act: 3.6431. Min Act: -0.0001
Data Index: 54785 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7561. Min Range: -4.7561
Max Act: 3.7926. Min Act: -0.0001
Data Index: 516921 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7561. Min Range: -4.7561
Max Act: 3.5652. Min Act: -0.0001
Data Index: 656441 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7561. Min Range: -4.7561
Max Act: 3.4240. Min Act: -0.0001
Data Index: 829371 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7561. Min Range: -4.7561
Max Act: 3.4135. Min Act: -0.0001
Data Index: 761741 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7561. Min Range: -4.7561
Max Act: 3.5569. Min Act: -0.0001
Data Index: 1141697 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7561. Min Range: -4.7561
Max Act: 3.3964. Min Act: -0.0001
Data Index: 1138686 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7561. Min Range: -4.7561
Max Act: 3.6796. Min Act: -0.0001
Data Index: 808595 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7561. Min Range: -4.7561
Max Act: 3.2150. Min Act: -0.0001
Data Index: 1320224 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7561. Min Range: -4.7561
Max Act: 3.3350. Min Act: -0.0001
Data Index: 902853 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19