Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1406 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0175. Min Act: -0.0001
Data Index: 376279 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0162. Min Act: -0.0001
Data Index: 847641 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0148. Min Act: -0.0001
Data Index: 769785 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0145. Min Act: -0.0001
Data Index: 170983 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0145. Min Act: -0.0001
Data Index: 612118 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0144. Min Act: -0.0001
Data Index: 697222 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0143. Min Act: -0.0001
Data Index: 1770327 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0140. Min Act: -0.0001
Data Index: 1611668 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0140. Min Act: -0.0001
Data Index: 1891746 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0139. Min Act: -0.0001
Data Index: 1785385 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0139. Min Act: -0.0001
Data Index: 1747425 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0138. Min Act: -0.0001
Data Index: 1920277 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0138. Min Act: -0.0001
Data Index: 1323338 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0138. Min Act: -0.0001
Data Index: 1908949 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0138. Min Act: -0.0001
Data Index: 949642 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0139. Min Act: -0.0001
Data Index: 1220999 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0133. Min Act: -0.0001
Data Index: 115700 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0133. Min Act: -0.0001
Data Index: 1640247 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0133. Min Act: -0.0001
Data Index: 1067378 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0175. Min Range: -0.0175
Max Act: 0.0132. Min Act: -0.0001
Data Index: 1951579 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19