Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 867 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.8518. Min Act: -0.0001
Data Index: 773069 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.9293. Min Act: -0.0001
Data Index: 1156567 (The Pile)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.8916. Min Act: -0.0001
Data Index: 72187 (The Pile)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.9114. Min Act: -0.0001
Data Index: 1640877 (The Pile)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.8033. Min Act: -0.0001
Data Index: 523267 (The Pile)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.5819. Min Act: -0.0001
Data Index: 1982368 (The Pile)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.8483. Min Act: -0.0001
Data Index: 1568744 (The Pile)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.6851. Min Act: -0.0001
Data Index: 691676 (The Pile)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.5040. Min Act: -0.0001
Data Index: 1907528 (The Pile)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.7068. Min Act: -0.0001
Data Index: 1187750 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.6916. Min Act: -0.0001
Data Index: 927338 (The Pile)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.2188. Min Act: -0.0001
Data Index: 1281267 (The Pile)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.8162. Min Act: -0.0001
Data Index: 541491 (The Pile)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.6468. Min Act: -0.0001
Data Index: 1769948 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.4073. Min Act: -0.0001
Data Index: 1640431 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.5238. Min Act: -0.0001
Data Index: 237999 (The Pile)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.2508. Min Act: -0.0001
Data Index: 720988 (The Pile)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.3857. Min Act: -0.0001
Data Index: 1484646 (The Pile)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.3551. Min Act: -0.0001
Data Index: 1779511 (The Pile)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9293. Min Range: -1.9293
Max Act: 1.4199. Min Act: -0.0001
Data Index: 428075 (The Pile)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19