Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5793 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8942. Min Range: -2.8942

Max Act: 2.8942. Min Act: -0.0000

Data Index: 977391 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 2.8942. Min Range: -2.8942

Max Act: 2.3273. Min Act: -0.0000

Data Index: 253409 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 2.8942. Min Range: -2.8942

Max Act: 2.0573. Min Act: -0.0000

Data Index: 1219586 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.8129. Min Act: -0.0000

Data Index: 866021 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.8804. Min Act: -0.0000

Data Index: 266763 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.7437. Min Act: -0.0000

Data Index: 1082426 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.8205. Min Act: -0.0000

Data Index: 559798 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.6216. Min Act: -0.0000

Data Index: 1278030 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.6942. Min Act: -0.0000

Data Index: 1242536 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.5550. Min Act: -0.0000

Data Index: 361112 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.7369. Min Act: -0.0000

Data Index: 491987 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.4736. Min Act: -0.0000

Data Index: 838794 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.3810. Min Act: -0.0000

Data Index: 458952 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.6261. Min Act: -0.0000

Data Index: 352887 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.4891. Min Act: -0.0000

Data Index: 235897 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.4748. Min Act: -0.0000

Data Index: 1334970 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.3429. Min Act: -0.0000

Data Index: 37590 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.4241. Min Act: -0.0000

Data Index: 1287007 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.4169. Min Act: -0.0000

Data Index: 916272 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 2.8942. Min Range: -2.8942

Max Act: 1.4128. Min Act: -0.0000

Data Index: 1138537 (C4 (Web Text))

Max Activating Token Index: 689