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

Dataset: The Pile

Neuron 2161 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: 0.4476. Min Range: -0.4476

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1619078 (The Pile)

Max Activating Token Index: 620

Text #1

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1463998 (The Pile)

Max Activating Token Index: 937

Text #2

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3515. Min Act: -0.0000

Data Index: 306280 (The Pile)

Max Activating Token Index: 928

Text #3

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3594. Min Act: -0.0000

Data Index: 841837 (The Pile)

Max Activating Token Index: 444

Text #4

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1777256 (The Pile)

Max Activating Token Index: 807

Text #5

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3145. Min Act: -0.0000

Data Index: 689773 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1172116 (The Pile)

Max Activating Token Index: 115

Text #7

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1354023 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1068071 (The Pile)

Max Activating Token Index: 684

Text #9

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1571308 (The Pile)

Max Activating Token Index: 367

Text #10

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3054. Min Act: -0.0000

Data Index: 192478 (The Pile)

Max Activating Token Index: 986

Text #11

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1930976 (The Pile)

Max Activating Token Index: 637

Text #12

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2979. Min Act: -0.0000

Data Index: 560501 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1127882 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2851. Min Act: -0.0000

Data Index: 658833 (The Pile)

Max Activating Token Index: 765

Text #15

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2930. Min Act: -0.0000

Data Index: 149938 (The Pile)

Max Activating Token Index: 729

Text #16

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1270220 (The Pile)

Max Activating Token Index: 63

Text #17

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2594. Min Act: -0.0000

Data Index: 108228 (The Pile)

Max Activating Token Index: 72

Text #18

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2688. Min Act: -0.0000

Data Index: 466790 (The Pile)

Max Activating Token Index: 779

Text #19

Max Range: 0.4476. Min Range: -0.4476

Max Act: 0.2808. Min Act: -0.0000

Data Index: 602086 (The Pile)

Max Activating Token Index: 243