Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 12 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.8323. Min Act: -0.0000
Data Index: 249862 (The Pile)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.7915. Min Act: -0.0000
Data Index: 1826019 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.6000. Min Act: -0.0000
Data Index: 1053295 (The Pile)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.5779. Min Act: -0.0000
Data Index: 1632263 (The Pile)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.6045. Min Act: -0.0000
Data Index: 1793202 (The Pile)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.5986. Min Act: -0.0000
Data Index: 1943522 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.6060. Min Act: -0.0000
Data Index: 1629439 (The Pile)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.4840. Min Act: -0.0000
Data Index: 125597 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.5613. Min Act: -0.0000
Data Index: 579815 (The Pile)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.5682. Min Act: -0.0000
Data Index: 1783118 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.4821. Min Act: -0.0000
Data Index: 1447537 (The Pile)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.4562. Min Act: -0.0000
Data Index: 1143351 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.3697. Min Act: -0.0000
Data Index: 1133071 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.5052. Min Act: -0.0000
Data Index: 706457 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.4428. Min Act: -0.0000
Data Index: 715355 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.4630. Min Act: -0.0000
Data Index: 403184 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.4526. Min Act: -0.0000
Data Index: 353816 (The Pile)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.4319. Min Act: -0.0000
Data Index: 1285844 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.4326. Min Act: -0.0000
Data Index: 1230821 (The Pile)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8323. Min Range: -1.8323
Max Act: 1.5591. Min Act: -0.0000
Data Index: 32013 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19