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

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

Neuron 2468 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5411. Min Range: -3.5411

Max Act: 3.5411. Min Act: -0.0000

Data Index: 306125 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 3.5411. Min Range: -3.5411

Max Act: 3.1330. Min Act: -0.0000

Data Index: 359545 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 3.5411. Min Range: -3.5411

Max Act: 3.0010. Min Act: -0.0000

Data Index: 912586 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.8755. Min Act: -0.0000

Data Index: 34613 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.7956. Min Act: -0.0000

Data Index: 1245619 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.7946. Min Act: -0.0000

Data Index: 135332 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.7739. Min Act: -0.0000

Data Index: 446191 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.6973. Min Act: -0.0000

Data Index: 665783 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.6663. Min Act: -0.0000

Data Index: 863415 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.5336. Min Act: -0.0000

Data Index: 735234 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.6037. Min Act: -0.0000

Data Index: 497245 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.5979. Min Act: -0.0000

Data Index: 580555 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.7108. Min Act: -0.0000

Data Index: 1309984 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.4253. Min Act: -0.0000

Data Index: 146542 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.5470. Min Act: -0.0000

Data Index: 1188505 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.4094. Min Act: -0.0000

Data Index: 890986 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.5201. Min Act: -0.0000

Data Index: 1327932 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.4132. Min Act: -0.0000

Data Index: 491682 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.5260. Min Act: -0.0000

Data Index: 1051508 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 3.5411. Min Range: -3.5411

Max Act: 2.3747. Min Act: -0.0000

Data Index: 474761 (C4 (Web Text))

Max Activating Token Index: 23