Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1000 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.7610. Min Act: -0.0001
Data Index: 146415 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.7980. Min Act: -0.0001
Data Index: 1781289 (The Pile)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.7359. Min Act: -0.0001
Data Index: 1071395 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.7175. Min Act: -0.0001
Data Index: 438950 (The Pile)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.6867. Min Act: -0.0001
Data Index: 545089 (The Pile)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.8022. Min Act: -0.0001
Data Index: 1228652 (The Pile)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.7131. Min Act: -0.0001
Data Index: 447427 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.6819. Min Act: -0.0001
Data Index: 320590 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.4622. Min Act: -0.0001
Data Index: 1150533 (The Pile)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.8508. Min Act: -0.0001
Data Index: 1650878 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.6782. Min Act: -0.0001
Data Index: 1953215 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.4925. Min Act: -0.0001
Data Index: 324039 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.5004. Min Act: -0.0001
Data Index: 1786349 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.4460. Min Act: -0.0001
Data Index: 10084 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.5275. Min Act: -0.0001
Data Index: 1719426 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.6325. Min Act: -0.0001
Data Index: 1288040 (The Pile)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.5247. Min Act: -0.0001
Data Index: 1768316 (The Pile)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.5345. Min Act: -0.0001
Data Index: 414955 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.4432. Min Act: -0.0001
Data Index: 905036 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8508. Min Range: -1.8508
Max Act: 1.5238. Min Act: -0.0001
Data Index: 337373 (The Pile)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19