Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1755 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.3129. Min Act: -0.0001
Data Index: 1959853 (The Pile)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2883. Min Act: -0.0001
Data Index: 195404 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.3148. Min Act: -0.0001
Data Index: 1573239 (The Pile)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2600. Min Act: -0.0001
Data Index: 847545 (The Pile)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2643. Min Act: -0.0001
Data Index: 1869663 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2416. Min Act: -0.0001
Data Index: 133529 (The Pile)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2698. Min Act: -0.0001
Data Index: 1513112 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2565. Min Act: -0.0001
Data Index: 449688 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2447. Min Act: -0.0001
Data Index: 1671958 (The Pile)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2538. Min Act: -0.0001
Data Index: 293608 (The Pile)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2499. Min Act: -0.0001
Data Index: 1920644 (The Pile)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2308. Min Act: -0.0001
Data Index: 897825 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2926. Min Act: -0.0001
Data Index: 1328379 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2583. Min Act: -0.0001
Data Index: 1208074 (The Pile)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2132. Min Act: -0.0001
Data Index: 1692538 (The Pile)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2347. Min Act: -0.0001
Data Index: 279288 (The Pile)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2472. Min Act: -0.0001
Data Index: 926324 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2338. Min Act: -0.0001
Data Index: 1071220 (The Pile)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2155. Min Act: -0.0001
Data Index: 34639 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3148. Min Range: -0.3148
Max Act: 0.2306. Min Act: -0.0001
Data Index: 1350671 (The Pile)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19