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

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

Neuron 774 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.4651. Min Act: -0.0001

Data Index: 1629549 (Python Code)

Max Activating Token Index: 823

Text #1

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3926. Min Act: -0.0000

Data Index: 1397064 (Python Code)

Max Activating Token Index: 699

Text #2

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.4047. Min Act: -0.0000

Data Index: 1656943 (Python Code)

Max Activating Token Index: 239

Text #3

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1560260 (Python Code)

Max Activating Token Index: 256

Text #4

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3989. Min Act: -0.0000

Data Index: 1388145 (Python Code)

Max Activating Token Index: 640

Text #5

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1572695 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1475926 (Python Code)

Max Activating Token Index: 554

Text #7

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1434455 (Python Code)

Max Activating Token Index: 786

Text #8

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3467. Min Act: -0.0001

Data Index: 1576109 (Python Code)

Max Activating Token Index: 525

Text #9

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1430565 (Python Code)

Max Activating Token Index: 566

Text #10

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1386675 (Python Code)

Max Activating Token Index: 247

Text #11

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1406167 (Python Code)

Max Activating Token Index: 625

Text #12

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3244. Min Act: -0.0001

Data Index: 1457559 (Python Code)

Max Activating Token Index: 1000

Text #13

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3097. Min Act: -0.0001

Data Index: 1615160 (Python Code)

Max Activating Token Index: 271

Text #14

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1575183 (Python Code)

Max Activating Token Index: 889

Text #15

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1512762 (Python Code)

Max Activating Token Index: 925

Text #16

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1543922 (Python Code)

Max Activating Token Index: 857

Text #17

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3044. Min Act: -0.0001

Data Index: 1450972 (Python Code)

Max Activating Token Index: 623

Text #18

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1479267 (Python Code)

Max Activating Token Index: 672

Text #19

Max Range: 0.4651. Min Range: -0.4651

Max Act: 0.2997. Min Act: -0.0001

Data Index: 1420339 (Python Code)

Max Activating Token Index: 553