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

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

Neuron 1985 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: 3.0853. Min Range: -3.0853

Max Act: 3.0853. Min Act: -0.0001

Data Index: 460208 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.9415. Min Act: -0.0001

Data Index: 511204 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.8034. Min Act: -0.0001

Data Index: 1132281 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.8319. Min Act: -0.0001

Data Index: 98123 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.6376. Min Act: -0.0001

Data Index: 719915 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.7520. Min Act: -0.0001

Data Index: 1070940 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.8790. Min Act: -0.0001

Data Index: 1030000 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.6973. Min Act: -0.0001

Data Index: 172234 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.4977. Min Act: -0.0001

Data Index: 425720 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.6273. Min Act: -0.0000

Data Index: 575056 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.7051. Min Act: -0.0001

Data Index: 143142 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.7084. Min Act: -0.0000

Data Index: 857503 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.6910. Min Act: -0.0000

Data Index: 710758 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.8029. Min Act: -0.0001

Data Index: 1206578 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.6673. Min Act: -0.0000

Data Index: 461455 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.5877. Min Act: -0.0001

Data Index: 9316 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.2242. Min Act: -0.0001

Data Index: 1124412 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.5485. Min Act: -0.0001

Data Index: 886288 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.6577. Min Act: -0.0001

Data Index: 18988 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 3.0853. Min Range: -3.0853

Max Act: 2.3346. Min Act: -0.0001

Data Index: 1220286 (C4 (Web Text))

Max Activating Token Index: 422