Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1699 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.5457. Min Act: -0.0000
Data Index: 417890 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.6124. Min Act: -0.0000
Data Index: 569042 (The Pile)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.5431. Min Act: -0.0000
Data Index: 1950611 (The Pile)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.4823. Min Act: -0.0000
Data Index: 213385 (The Pile)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.5132. Min Act: -0.0000
Data Index: 1361341 (The Pile)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.5144. Min Act: -0.0000
Data Index: 1348551 (The Pile)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.4547. Min Act: -0.0000
Data Index: 21689 (The Pile)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.2283. Min Act: -0.0000
Data Index: 85017 (The Pile)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.3039. Min Act: -0.0000
Data Index: 1259389 (The Pile)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.2807. Min Act: -0.0000
Data Index: 207965 (The Pile)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.1381. Min Act: -0.0000
Data Index: 347193 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.3831. Min Act: -0.0000
Data Index: 332582 (The Pile)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.2512. Min Act: -0.0000
Data Index: 1412070 (The Pile)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.2332. Min Act: -0.0000
Data Index: 1712080 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.5887. Min Act: -0.0000
Data Index: 1475793 (The Pile)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.4445. Min Act: -0.0000
Data Index: 657976 (The Pile)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.3385. Min Act: -0.0000
Data Index: 1189862 (The Pile)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.3471. Min Act: -0.0000
Data Index: 731175 (The Pile)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.2122. Min Act: -0.0000
Data Index: 109124 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6124. Min Range: -2.6124
Max Act: 2.4351. Min Act: -0.0000
Data Index: 508543 (The Pile)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19