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

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

Neuron 3294 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.5960. Min Act: -0.0000

Data Index: 1050140 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.4944. Min Act: -0.0000

Data Index: 1018712 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.3965. Min Act: -0.0000

Data Index: 416567 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.2405. Min Act: -0.0000

Data Index: 766101 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.2899. Min Act: -0.0000

Data Index: 402125 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.3139. Min Act: -0.0001

Data Index: 1245563 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.3110. Min Act: -0.0000

Data Index: 1297543 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0521. Min Act: -0.0000

Data Index: 61585 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.2044. Min Act: -0.0000

Data Index: 1078202 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0374. Min Act: -0.0001

Data Index: 957990 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0842. Min Act: -0.0000

Data Index: 165744 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.1132. Min Act: -0.0000

Data Index: 1319683 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.1361. Min Act: -0.0001

Data Index: 955438 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0653. Min Act: -0.0000

Data Index: 816807 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0179. Min Act: -0.0000

Data Index: 447201 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.1087. Min Act: -0.0001

Data Index: 380061 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0621. Min Act: -0.0000

Data Index: 730457 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.9948. Min Act: -0.0000

Data Index: 49630 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0661. Min Act: -0.0000

Data Index: 814857 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0345. Min Act: -0.0000

Data Index: 612871 (C4 (Web Text))

Max Activating Token Index: 317