Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1723 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.7932. Min Act: -0.0001
Data Index: 278995 (The Pile)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.5135. Min Act: -0.0001
Data Index: 1373652 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.3449. Min Act: -0.0001
Data Index: 698972 (The Pile)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.8307. Min Act: -0.0001
Data Index: 1335834 (The Pile)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.5058. Min Act: -0.0001
Data Index: 1449311 (The Pile)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.8182. Min Act: -0.0001
Data Index: 1173278 (The Pile)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.4728. Min Act: -0.0001
Data Index: 1826608 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.4642. Min Act: -0.0001
Data Index: 1617845 (The Pile)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.4335. Min Act: -0.0001
Data Index: 1377427 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.5384. Min Act: -0.0001
Data Index: 1909250 (The Pile)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.2035. Min Act: -0.0001
Data Index: 1650766 (The Pile)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.3440. Min Act: -0.0001
Data Index: 620348 (The Pile)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.4961. Min Act: -0.0001
Data Index: 190041 (The Pile)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.4891. Min Act: -0.0000
Data Index: 893211 (The Pile)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.6229. Min Act: -0.0001
Data Index: 910430 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.2056. Min Act: -0.0001
Data Index: 468149 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.4796. Min Act: -0.0001
Data Index: 50879 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.3333. Min Act: -0.0001
Data Index: 1875807 (The Pile)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.1586. Min Act: -0.0001
Data Index: 771897 (The Pile)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8307. Min Range: -3.8307
Max Act: 3.6214. Min Act: -0.0001
Data Index: 167224 (The Pile)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19