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

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

Neuron 3565 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1953. Min Range: -2.1953

Max Act: 2.1953. Min Act: -0.0001

Data Index: 338347 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.7976. Min Act: -0.0001

Data Index: 209481 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.8319. Min Act: -0.0001

Data Index: 235553 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.5800. Min Act: -0.0001

Data Index: 66282 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.7066. Min Act: -0.0001

Data Index: 928208 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.5955. Min Act: -0.0001

Data Index: 1087843 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.6417. Min Act: -0.0001

Data Index: 238987 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.6891. Min Act: -0.0001

Data Index: 934158 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.6437. Min Act: -0.0001

Data Index: 1181971 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.5952. Min Act: -0.0001

Data Index: 724129 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.5297. Min Act: -0.0001

Data Index: 31848 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.6938. Min Act: -0.0001

Data Index: 907720 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.5797. Min Act: -0.0001

Data Index: 1137786 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.5900. Min Act: -0.0001

Data Index: 785947 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.5868. Min Act: -0.0001

Data Index: 323160 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.5366. Min Act: -0.0001

Data Index: 125621 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.5247. Min Act: -0.0001

Data Index: 457782 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.5275. Min Act: -0.0001

Data Index: 691844 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.6142. Min Act: -0.0001

Data Index: 1236564 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 2.1953. Min Range: -2.1953

Max Act: 1.6737. Min Act: -0.0001

Data Index: 1085912 (C4 (Web Text))

Max Activating Token Index: 101