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

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

Neuron 213 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.6019. Min Act: -0.0000

Data Index: 923684 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1194798 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5158. Min Act: -0.0000

Data Index: 964667 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5136. Min Act: -0.0001

Data Index: 247562 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4949. Min Act: -0.0001

Data Index: 495314 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5240. Min Act: -0.0001

Data Index: 816275 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1079040 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5020. Min Act: -0.0000

Data Index: 1164793 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4740. Min Act: -0.0000

Data Index: 754549 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4834. Min Act: -0.0001

Data Index: 114779 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4420. Min Act: -0.0001

Data Index: 719955 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4309. Min Act: -0.0001

Data Index: 508969 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4239. Min Act: -0.0001

Data Index: 1076334 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4225. Min Act: -0.0000

Data Index: 966089 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4312. Min Act: -0.0000

Data Index: 99501 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4307. Min Act: -0.0000

Data Index: 757496 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3975. Min Act: -0.0000

Data Index: 1069479 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4085. Min Act: -0.0001

Data Index: 621919 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4027. Min Act: -0.0000

Data Index: 4995 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3816. Min Act: -0.0001

Data Index: 1273820 (C4 (Web Text))

Max Activating Token Index: 132