Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 860 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0219. Min Act: -0.0001
Data Index: 290601 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0165. Min Act: -0.0001
Data Index: 1373048 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0142. Min Act: -0.0001
Data Index: 1425990 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0142. Min Act: -0.0001
Data Index: 969918 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0142. Min Act: -0.0001
Data Index: 1923480 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0138. Min Act: -0.0001
Data Index: 421706 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0148. Min Act: -0.0001
Data Index: 701468 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0142. Min Act: -0.0001
Data Index: 1040321 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0129. Min Act: -0.0001
Data Index: 750941 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0129. Min Act: -0.0001
Data Index: 324368 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0129. Min Act: -0.0001
Data Index: 335648 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0138. Min Act: -0.0001
Data Index: 45757 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0136. Min Act: -0.0001
Data Index: 332667 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0136. Min Act: -0.0001
Data Index: 1101836 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0138. Min Act: -0.0001
Data Index: 1926772 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0132. Min Act: -0.0001
Data Index: 792987 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0131. Min Act: -0.0001
Data Index: 628547 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0140. Min Act: -0.0001
Data Index: 1138561 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0140. Min Act: -0.0001
Data Index: 942627 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0219. Min Range: -0.0219
Max Act: 0.0132. Min Act: -0.0001
Data Index: 1222949 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19