Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 873 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.6320. Min Act: -0.0001
Data Index: 511290 (The Pile)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.5187. Min Act: -0.0001
Data Index: 1428541 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.4088. Min Act: -0.0001
Data Index: 569882 (The Pile)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.4106. Min Act: -0.0001
Data Index: 565867 (The Pile)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.2532. Min Act: -0.0001
Data Index: 440750 (The Pile)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.2135. Min Act: -0.0000
Data Index: 1831395 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.3392. Min Act: -0.0001
Data Index: 1916369 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.5030. Min Act: -0.0001
Data Index: 702938 (The Pile)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.4123. Min Act: -0.0001
Data Index: 316007 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.2546. Min Act: -0.0000
Data Index: 434863 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.1848. Min Act: -0.0001
Data Index: 1679676 (The Pile)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.2000. Min Act: -0.0001
Data Index: 1220017 (The Pile)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.0110. Min Act: -0.0001
Data Index: 800633 (The Pile)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.1462. Min Act: -0.0001
Data Index: 1026500 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.0304. Min Act: -0.0000
Data Index: 1955209 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.2708. Min Act: -0.0000
Data Index: 693790 (The Pile)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6320. Min Range: -3.6320
Max Act: 2.9773. Min Act: -0.0000
Data Index: 1023715 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.1099. Min Act: -0.0001
Data Index: 1013724 (The Pile)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6320. Min Range: -3.6320
Max Act: 3.0735. Min Act: -0.0001
Data Index: 1424830 (The Pile)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6320. Min Range: -3.6320
Max Act: 2.9117. Min Act: -0.0001
Data Index: 1927710 (The Pile)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19