Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3968 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.0233. Min Range: -1.0233
Max Act: 1.0233. Min Act: -0.0001
Data Index: 1832597 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.8668. Min Act: -0.0001
Data Index: 744501 (The Pile)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.8388. Min Act: -0.0001
Data Index: 54094 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.8618. Min Act: -0.0001
Data Index: 56747 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.8955. Min Act: -0.0001
Data Index: 1419015 (The Pile)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.8372. Min Act: -0.0001
Data Index: 424847 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.7960. Min Act: -0.0001
Data Index: 1302304 (The Pile)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.8477. Min Act: -0.0001
Data Index: 137155 (The Pile)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.8154. Min Act: -0.0001
Data Index: 961695 (The Pile)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.8165. Min Act: -0.0001
Data Index: 1799977 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.7984. Min Act: -0.0001
Data Index: 786920 (The Pile)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.8058. Min Act: -0.0001
Data Index: 1953363 (The Pile)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.8333. Min Act: -0.0001
Data Index: 1630510 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.8113. Min Act: -0.0001
Data Index: 1821185 (The Pile)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.8116. Min Act: -0.0001
Data Index: 433661 (The Pile)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.7999. Min Act: -0.0001
Data Index: 1630166 (The Pile)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.7748. Min Act: -0.0001
Data Index: 188967 (The Pile)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.7945. Min Act: -0.0001
Data Index: 1816333 (The Pile)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.7637. Min Act: -0.0001
Data Index: 577722 (The Pile)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0233. Min Range: -1.0233
Max Act: 0.7624. Min Act: -0.0001
Data Index: 1761084 (The Pile)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19