Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 948 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1234. Min Act: -0.0001
Data Index: 1747829 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1165. Min Act: -0.0001
Data Index: 1957398 (The Pile)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1104. Min Act: -0.0001
Data Index: 1427775 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1155. Min Act: -0.0001
Data Index: 834540 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1148. Min Act: -0.0001
Data Index: 1034914 (The Pile)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1104. Min Act: -0.0001
Data Index: 112564 (The Pile)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1020. Min Act: -0.0001
Data Index: 951021 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1063. Min Act: -0.0001
Data Index: 1453086 (The Pile)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1063. Min Act: -0.0001
Data Index: 1930802 (The Pile)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1141. Min Act: -0.0001
Data Index: 642710 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1048. Min Act: -0.0001
Data Index: 1517214 (The Pile)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1123. Min Act: -0.0001
Data Index: 1956869 (The Pile)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.0846. Min Act: -0.0001
Data Index: 780600 (The Pile)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1136. Min Act: -0.0001
Data Index: 483060 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1054. Min Act: -0.0001
Data Index: 1166327 (The Pile)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1066. Min Act: -0.0001
Data Index: 699876 (The Pile)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.0986. Min Act: -0.0001
Data Index: 1490101 (The Pile)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.0974. Min Act: -0.0001
Data Index: 1998740 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.1106. Min Act: -0.0001
Data Index: 1822773 (The Pile)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1234. Min Range: -0.1234
Max Act: 0.0968. Min Act: -0.0001
Data Index: 1739459 (The Pile)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19