Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4764 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4714. Min Act: -0.0000

Data Index: 955292 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3705. Min Act: -0.0000

Data Index: 252061 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1167756 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3514. Min Act: -0.0000

Data Index: 909420 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3082. Min Act: -0.0000

Data Index: 59844 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2948. Min Act: -0.0000

Data Index: 706183 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3342. Min Act: -0.0000

Data Index: 14492 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3250. Min Act: -0.0000

Data Index: 681811 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1220234 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3265. Min Act: -0.0000

Data Index: 701376 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2802. Min Act: -0.0000

Data Index: 626294 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3022. Min Act: -0.0000

Data Index: 4201 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1061954 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1060696 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3043. Min Act: -0.0000

Data Index: 772946 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1271269 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2927. Min Act: -0.0000

Data Index: 503313 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2926. Min Act: -0.0000

Data Index: 913330 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2828. Min Act: -0.0000

Data Index: 555866 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.2801. Min Act: -0.0000

Data Index: 329534 (C4 (Web Text))

Max Activating Token Index: 669