Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1500 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.4244. Min Act: -0.0000

Data Index: 62140 (The Pile)

Max Activating Token Index: 214

Text #1

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3938. Min Act: -0.0000

Data Index: 708525 (The Pile)

Max Activating Token Index: 1015

Text #2

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3401. Min Act: -0.0000

Data Index: 526768 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3624. Min Act: -0.0000

Data Index: 644556 (The Pile)

Max Activating Token Index: 573

Text #4

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3814. Min Act: -0.0000

Data Index: 208398 (The Pile)

Max Activating Token Index: 676

Text #5

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1040954 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3896. Min Act: -0.0000

Data Index: 862488 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1706029 (The Pile)

Max Activating Token Index: 902

Text #8

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3369. Min Act: -0.0000

Data Index: 54248 (The Pile)

Max Activating Token Index: 809

Text #9

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1720266 (The Pile)

Max Activating Token Index: 887

Text #10

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1522738 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3253. Min Act: -0.0000

Data Index: 714956 (The Pile)

Max Activating Token Index: 446

Text #12

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3427. Min Act: -0.0000

Data Index: 23550 (The Pile)

Max Activating Token Index: 492

Text #13

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3437. Min Act: -0.0000

Data Index: 14225 (The Pile)

Max Activating Token Index: 656

Text #14

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3053. Min Act: -0.0000

Data Index: 926905 (The Pile)

Max Activating Token Index: 846

Text #15

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1768316 (The Pile)

Max Activating Token Index: 853

Text #16

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1800486 (The Pile)

Max Activating Token Index: 736

Text #17

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1361938 (The Pile)

Max Activating Token Index: 387

Text #18

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1258930 (The Pile)

Max Activating Token Index: 953

Text #19

Max Range: 0.4244. Min Range: -0.4244

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1605075 (The Pile)

Max Activating Token Index: 570