Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1011 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.4148. Min Act: -0.0000
Data Index: 1151029 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.4072. Min Act: -0.0000
Data Index: 544035 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.3722. Min Act: -0.0000
Data Index: 112750 (The Pile)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.3469. Min Act: 0.0000
Data Index: 1836171 (The Pile)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.3546. Min Act: 0.0001
Data Index: 1934437 (The Pile)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.3319. Min Act: 0.0000
Data Index: 1170310 (The Pile)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.3395. Min Act: -0.0000
Data Index: 1577897 (The Pile)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.3236. Min Act: -0.0000
Data Index: 32513 (The Pile)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.3075. Min Act: 0.0002
Data Index: 1521001 (The Pile)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.3241. Min Act: 0.0000
Data Index: 1126316 (The Pile)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.3102. Min Act: 0.0000
Data Index: 1407429 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.2978. Min Act: 0.0001
Data Index: 1609814 (The Pile)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.2952. Min Act: -0.0000
Data Index: 1533001 (The Pile)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.2998. Min Act: 0.0001
Data Index: 982385 (The Pile)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.2981. Min Act: -0.0000
Data Index: 1915735 (The Pile)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.2870. Min Act: -0.0000
Data Index: 854718 (The Pile)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.2887. Min Act: 0.0000
Data Index: 1029450 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.2882. Min Act: -0.0000
Data Index: 148306 (The Pile)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.2934. Min Act: 0.0000
Data Index: 3666 (The Pile)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4148. Min Range: -0.4148
Max Act: 0.2974. Min Act: 0.0000
Data Index: 1861703 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19