Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 984 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.3543. Min Act: -0.0000

Data Index: 995965 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.3234. Min Act: -0.0000

Data Index: 1026092 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 3.3543. Min Range: -3.3543

Max Act: 2.9464. Min Act: -0.0000

Data Index: 248257 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.1455. Min Act: -0.0000

Data Index: 96475 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.0010. Min Act: -0.0000

Data Index: 460263 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.1174. Min Act: -0.0000

Data Index: 1023704 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 3.3543. Min Range: -3.3543

Max Act: 2.6672. Min Act: -0.0000

Data Index: 28870 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.0622. Min Act: -0.0000

Data Index: 132243 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 3.3543. Min Range: -3.3543

Max Act: 2.8608. Min Act: -0.0000

Data Index: 925017 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 3.3543. Min Range: -3.3543

Max Act: 2.8053. Min Act: -0.0000

Data Index: 370920 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 3.3543. Min Range: -3.3543

Max Act: 2.8142. Min Act: -0.0000

Data Index: 373637 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 3.3543. Min Range: -3.3543

Max Act: 2.5374. Min Act: -0.0000

Data Index: 265471 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 3.3543. Min Range: -3.3543

Max Act: 2.6493. Min Act: -0.0000

Data Index: 15504 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 3.3543. Min Range: -3.3543

Max Act: 2.6051. Min Act: -0.0000

Data Index: 913620 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 3.3543. Min Range: -3.3543

Max Act: 2.8088. Min Act: -0.0000

Data Index: 368479 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 3.3543. Min Range: -3.3543

Max Act: 2.6068. Min Act: -0.0000

Data Index: 1205003 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 3.3543. Min Range: -3.3543

Max Act: 2.6039. Min Act: -0.0000

Data Index: 975506 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 3.3543. Min Range: -3.3543

Max Act: 2.7262. Min Act: -0.0000

Data Index: 551534 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 3.3543. Min Range: -3.3543

Max Act: 2.7049. Min Act: -0.0000

Data Index: 1217207 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 3.3543. Min Range: -3.3543

Max Act: 2.7045. Min Act: -0.0000

Data Index: 166963 (C4 (Web Text))

Max Activating Token Index: 604