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

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

Neuron 3954 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.7744. Min Act: -0.0001

Data Index: 485449 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.8041. Min Act: -0.0001

Data Index: 1080261 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.7416. Min Act: -0.0001

Data Index: 831506 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.7656. Min Act: -0.0001

Data Index: 700565 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.7627. Min Act: -0.0001

Data Index: 859969 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6883. Min Act: -0.0001

Data Index: 1202783 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.7448. Min Act: -0.0001

Data Index: 725951 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6753. Min Act: -0.0001

Data Index: 894049 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6969. Min Act: -0.0001

Data Index: 784972 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6730. Min Act: -0.0001

Data Index: 48065 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6521. Min Act: -0.0001

Data Index: 404140 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5964. Min Act: -0.0001

Data Index: 53411 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6466. Min Act: -0.0001

Data Index: 817237 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6336. Min Act: -0.0001

Data Index: 694560 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6034. Min Act: -0.0001

Data Index: 1166094 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6240. Min Act: -0.0001

Data Index: 752628 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6218. Min Act: -0.0001

Data Index: 883705 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5995. Min Act: -0.0001

Data Index: 853788 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6387. Min Act: -0.0001

Data Index: 1020266 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6138. Min Act: -0.0001

Data Index: 586825 (C4 (Web Text))

Max Activating Token Index: 613