Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2601 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3582. Min Act: -0.0001
Data Index: 1675275 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3453. Min Act: -0.0001
Data Index: 631805 (The Pile)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3400. Min Act: -0.0001
Data Index: 214199 (The Pile)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3370. Min Act: -0.0001
Data Index: 873602 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3344. Min Act: -0.0001
Data Index: 1340910 (The Pile)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3334. Min Act: -0.0001
Data Index: 428433 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3182. Min Act: -0.0001
Data Index: 1661001 (The Pile)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3291. Min Act: -0.0002
Data Index: 1029098 (The Pile)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3274. Min Act: -0.0001
Data Index: 594968 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3368. Min Act: -0.0001
Data Index: 633972 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3260. Min Act: -0.0001
Data Index: 613986 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3350. Min Act: -0.0001
Data Index: 1349055 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3241. Min Act: -0.0001
Data Index: 1763575 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3198. Min Act: -0.0002
Data Index: 907129 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3097. Min Act: -0.0001
Data Index: 921654 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3181. Min Act: -0.0001
Data Index: 938712 (The Pile)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3072. Min Act: -0.0001
Data Index: 30373 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3199. Min Act: -0.0001
Data Index: 1925056 (The Pile)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3177. Min Act: -0.0001
Data Index: 1123613 (The Pile)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3582. Min Range: -0.3582
Max Act: 0.3147. Min Act: -0.0001
Data Index: 1388367 (The Pile)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19