Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3003 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0277. Min Act: -0.0000
Data Index: 1312028 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0277. Min Act: 0.0002
Data Index: 142263 (The Pile)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0264. Min Act: -0.0000
Data Index: 1632010 (The Pile)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0273. Min Act: 0.0000
Data Index: 1401083 (The Pile)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0265. Min Act: 0.0001
Data Index: 1259798 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0264. Min Act: 0.0000
Data Index: 331024 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0263. Min Act: 0.0000
Data Index: 1975921 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0262. Min Act: -0.0000
Data Index: 1536740 (The Pile)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0258. Min Act: -0.0000
Data Index: 12809 (The Pile)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0257. Min Act: 0.0000
Data Index: 837294 (The Pile)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0257. Min Act: -0.0000
Data Index: 1658458 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0257. Min Act: -0.0000
Data Index: 1863821 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0256. Min Act: -0.0000
Data Index: 28454 (The Pile)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0257. Min Act: -0.0000
Data Index: 40477 (The Pile)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0257. Min Act: 0.0000
Data Index: 832265 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0255. Min Act: -0.0001
Data Index: 1684196 (The Pile)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0255. Min Act: 0.0000
Data Index: 59255 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0255. Min Act: -0.0000
Data Index: 518799 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0254. Min Act: -0.0000
Data Index: 341006 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0277. Min Range: -0.0277
Max Act: 0.0254. Min Act: -0.0000
Data Index: 1034203 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19