Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1283 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.9311. Min Act: -0.0001
Data Index: 1052944 (The Pile)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.6704. Min Act: -0.0001
Data Index: 930188 (The Pile)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.7455. Min Act: -0.0001
Data Index: 1305704 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.5748. Min Act: -0.0001
Data Index: 1744839 (The Pile)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.5544. Min Act: -0.0001
Data Index: 495522 (The Pile)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.6801. Min Act: -0.0001
Data Index: 1049601 (The Pile)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.6140. Min Act: -0.0001
Data Index: 56854 (The Pile)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.6468. Min Act: -0.0001
Data Index: 863078 (The Pile)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.4618. Min Act: -0.0001
Data Index: 686534 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.4986. Min Act: -0.0001
Data Index: 5218 (The Pile)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.4234. Min Act: -0.0001
Data Index: 277712 (The Pile)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.5423. Min Act: -0.0001
Data Index: 1369271 (The Pile)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.4916. Min Act: -0.0001
Data Index: 1977082 (The Pile)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.5626. Min Act: -0.0001
Data Index: 235156 (The Pile)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.7814. Min Act: -0.0001
Data Index: 929629 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.3724. Min Act: -0.0001
Data Index: 1440418 (The Pile)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.4062. Min Act: -0.0001
Data Index: 1328186 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.4411. Min Act: -0.0001
Data Index: 1423159 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.3934. Min Act: -0.0001
Data Index: 995765 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9311. Min Range: -1.9311
Max Act: 1.4357. Min Act: -0.0001
Data Index: 189322 (The Pile)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19