Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 386 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3107. Min Act: -0.0001
Data Index: 1225726 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3268. Min Act: -0.0001
Data Index: 1147051 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3364. Min Act: -0.0001
Data Index: 913371 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3229. Min Act: -0.0001
Data Index: 767213 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3244. Min Act: -0.0001
Data Index: 1637758 (Python Code)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3184. Min Act: -0.0001
Data Index: 312982 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3171. Min Act: -0.0001
Data Index: 347716 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3165. Min Act: -0.0001
Data Index: 209538 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3044. Min Act: -0.0001
Data Index: 1477419 (Python Code)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3136. Min Act: -0.0001
Data Index: 1270728 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3228. Min Act: -0.0001
Data Index: 288273 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3118. Min Act: -0.0001
Data Index: 593817 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.2999. Min Act: -0.0001
Data Index: 89754 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3096. Min Act: -0.0001
Data Index: 596857 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3051. Min Act: -0.0001
Data Index: 111114 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3069. Min Act: -0.0001
Data Index: 240775 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3080. Min Act: -0.0001
Data Index: 1086003 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.2995. Min Act: -0.0001
Data Index: 1151348 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3076. Min Act: -0.0001
Data Index: 601538 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3364. Min Range: -0.3364
Max Act: 0.3074. Min Act: -0.0001
Data Index: 896221 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19