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

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

Neuron 623 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3777. Min Act: -0.0001

Data Index: 1221185 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3557. Min Act: -0.0001

Data Index: 577640 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3372. Min Act: -0.0001

Data Index: 895761 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3552. Min Act: -0.0001

Data Index: 321165 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3554. Min Act: -0.0001

Data Index: 325081 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3381. Min Act: -0.0001

Data Index: 979252 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.2992. Min Act: -0.0001

Data Index: 1329806 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3332. Min Act: -0.0001

Data Index: 948623 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.2903. Min Act: -0.0001

Data Index: 1094453 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3174. Min Act: -0.0001

Data Index: 798345 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3071. Min Act: -0.0001

Data Index: 235392 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3348. Min Act: -0.0001

Data Index: 655183 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3260. Min Act: -0.0001

Data Index: 962734 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.2897. Min Act: -0.0001

Data Index: 1348792 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3062. Min Act: -0.0001

Data Index: 152042 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3047. Min Act: -0.0001

Data Index: 1190741 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.3087. Min Act: -0.0001

Data Index: 50192 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.2802. Min Act: -0.0001

Data Index: 852630 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.2930. Min Act: -0.0001

Data Index: 101686 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.3777. Min Range: -0.3777

Max Act: 0.2915. Min Act: -0.0001

Data Index: 370655 (C4 (Web Text))

Max Activating Token Index: 168