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

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

Neuron 650 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.9871. Min Act: -0.0001

Data Index: 1109661 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.6442. Min Act: -0.0001

Data Index: 1143529 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.5956. Min Act: -0.0001

Data Index: 3307 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.5553. Min Act: -0.0001

Data Index: 822668 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.5961. Min Act: -0.0001

Data Index: 925954 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.5028. Min Act: -0.0001

Data Index: 1204305 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.5574. Min Act: -0.0001

Data Index: 493301 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.4472. Min Act: -0.0001

Data Index: 403931 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.4771. Min Act: -0.0001

Data Index: 828475 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.4873. Min Act: -0.0001

Data Index: 658829 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.3946. Min Act: -0.0001

Data Index: 153808 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.4061. Min Act: -0.0001

Data Index: 1302518 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.3942. Min Act: -0.0001

Data Index: 498789 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.4202. Min Act: -0.0001

Data Index: 757112 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.3830. Min Act: -0.0001

Data Index: 327037 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.4572. Min Act: -0.0001

Data Index: 1053232 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.4662. Min Act: -0.0001

Data Index: 882980 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.4034. Min Act: -0.0001

Data Index: 183267 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.3602. Min Act: -0.0001

Data Index: 102379 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 2.9871. Min Range: -2.9871

Max Act: 2.4581. Min Act: -0.0001

Data Index: 1158255 (C4 (Web Text))

Max Activating Token Index: 348