Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 32 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.7104. Min Act: -0.0001
Data Index: 527511 (The Pile)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.6482. Min Act: -0.0001
Data Index: 1824376 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.4458. Min Act: -0.0001
Data Index: 1725683 (The Pile)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.3358. Min Act: -0.0001
Data Index: 1873118 (The Pile)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.3767. Min Act: -0.0001
Data Index: 1608212 (The Pile)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.4895. Min Act: -0.0001
Data Index: 746943 (The Pile)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.4599. Min Act: -0.0001
Data Index: 527780 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.3768. Min Act: -0.0001
Data Index: 870202 (The Pile)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.5749. Min Act: -0.0001
Data Index: 1709251 (The Pile)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.3256. Min Act: -0.0001
Data Index: 670026 (The Pile)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.3277. Min Act: -0.0001
Data Index: 984823 (The Pile)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.3019. Min Act: -0.0001
Data Index: 836255 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.2407. Min Act: -0.0001
Data Index: 1115182 (The Pile)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.3474. Min Act: -0.0001
Data Index: 143110 (The Pile)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.2863. Min Act: -0.0001
Data Index: 1872285 (The Pile)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.2699. Min Act: -0.0001
Data Index: 1345049 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.2140. Min Act: -0.0001
Data Index: 202127 (The Pile)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.2259. Min Act: -0.0001
Data Index: 1006671 (The Pile)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.1999. Min Act: -0.0001
Data Index: 1501432 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7104. Min Range: -1.7104
Max Act: 1.2260. Min Act: -0.0001
Data Index: 1260838 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19