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

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

Neuron 61 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3942. Min Act: -0.0001

Data Index: 1062424 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3447. Min Act: -0.0001

Data Index: 490973 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3341. Min Act: -0.0001

Data Index: 815487 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3339. Min Act: -0.0001

Data Index: 531369 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3169. Min Act: -0.0001

Data Index: 679437 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3404. Min Act: -0.0001

Data Index: 990500 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3162. Min Act: -0.0001

Data Index: 779631 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3120. Min Act: -0.0001

Data Index: 606996 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3093. Min Act: -0.0001

Data Index: 1179502 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2979. Min Act: -0.0001

Data Index: 852300 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3008. Min Act: -0.0001

Data Index: 999208 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2884. Min Act: -0.0001

Data Index: 1120426 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2945. Min Act: -0.0001

Data Index: 734154 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2862. Min Act: -0.0001

Data Index: 1071200 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3041. Min Act: -0.0001

Data Index: 651927 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3050. Min Act: -0.0001

Data Index: 771925 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.3025. Min Act: -0.0001

Data Index: 713669 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2904. Min Act: -0.0001

Data Index: 768459 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2898. Min Act: -0.0001

Data Index: 160667 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.3942. Min Range: -0.3942

Max Act: 0.2897. Min Act: -0.0001

Data Index: 1100478 (C4 (Web Text))

Max Activating Token Index: 173