Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6060 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.1593. Min Act: -0.0001
Data Index: 812148 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.1236. Min Act: -0.0001
Data Index: 321512 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.1128. Min Act: -0.0001
Data Index: 227098 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.1117. Min Act: -0.0001
Data Index: 517568 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.1173. Min Act: -0.0001
Data Index: 1440353 (Python Code)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.1104. Min Act: -0.0001
Data Index: 351394 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.1120. Min Act: -0.0001
Data Index: 222213 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.1058. Min Act: -0.0001
Data Index: 567803 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.0970. Min Act: -0.0001
Data Index: 267816 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.1081. Min Act: -0.0001
Data Index: 122783 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.1052. Min Act: -0.0001
Data Index: 793042 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.1004. Min Act: -0.0001
Data Index: 1355902 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.1026. Min Act: -0.0001
Data Index: 1361718 (Python Code)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.1027. Min Act: -0.0001
Data Index: 968396 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.0980. Min Act: -0.0001
Data Index: 81443 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.1033. Min Act: -0.0001
Data Index: 1262795 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.0981. Min Act: -0.0001
Data Index: 48942 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.0983. Min Act: -0.0001
Data Index: 549000 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.0975. Min Act: -0.0001
Data Index: 65126 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1593. Min Range: -0.1593
Max Act: 0.1007. Min Act: -0.0001
Data Index: 901003 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19