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

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

Neuron 938 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3576. Min Act: -0.0001

Data Index: 1201979 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3841. Min Act: -0.0001

Data Index: 867206 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3614. Min Act: -0.0001

Data Index: 76010 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3273. Min Act: -0.0001

Data Index: 914320 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3329. Min Act: -0.0001

Data Index: 17534 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3133. Min Act: -0.0001

Data Index: 1027410 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3211. Min Act: -0.0001

Data Index: 917128 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3318. Min Act: -0.0001

Data Index: 91817 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3322. Min Act: -0.0001

Data Index: 454957 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3293. Min Act: -0.0001

Data Index: 1128589 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3158. Min Act: -0.0001

Data Index: 736623 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3360. Min Act: -0.0001

Data Index: 615241 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3340. Min Act: -0.0001

Data Index: 1096916 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3171. Min Act: -0.0001

Data Index: 355992 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3052. Min Act: -0.0001

Data Index: 595023 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3130. Min Act: -0.0001

Data Index: 1095037 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3266. Min Act: -0.0001

Data Index: 330903 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2915. Min Act: -0.0001

Data Index: 983966 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3219. Min Act: -0.0001

Data Index: 893037 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3308. Min Act: -0.0001

Data Index: 516329 (C4 (Web Text))

Max Activating Token Index: 830