Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2215 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4422. Min Act: -0.0001

Data Index: 710347 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3683. Min Act: -0.0001

Data Index: 538249 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3332. Min Act: -0.0001

Data Index: 80879 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3696. Min Act: -0.0000

Data Index: 126184 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3588. Min Act: -0.0001

Data Index: 916586 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3029. Min Act: -0.0001

Data Index: 751111 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3298. Min Act: -0.0001

Data Index: 650908 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3147. Min Act: -0.0001

Data Index: 122215 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3172. Min Act: -0.0001

Data Index: 509024 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3042. Min Act: -0.0001

Data Index: 290113 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1347562 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3002. Min Act: -0.0001

Data Index: 459951 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2907. Min Act: -0.0001

Data Index: 437548 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2978. Min Act: -0.0001

Data Index: 949355 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2884. Min Act: -0.0001

Data Index: 111471 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2903. Min Act: -0.0001

Data Index: 390665 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2832. Min Act: -0.0001

Data Index: 136309 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2898. Min Act: -0.0001

Data Index: 159176 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2876. Min Act: -0.0000

Data Index: 532178 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2761. Min Act: -0.0001

Data Index: 649804 (C4 (Web Text))

Max Activating Token Index: 140