Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 953 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.4761. Min Act: -0.1700

Data Index: 1231999 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.3192. Min Act: -0.1700

Data Index: 239522 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.3192. Min Act: -0.1700

Data Index: 443249 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.2878. Min Act: -0.1700

Data Index: 708904 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.2878. Min Act: -0.1700

Data Index: 789288 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.2878. Min Act: -0.1700

Data Index: 108738 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.2878. Min Act: -0.1700

Data Index: 27917 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.2564. Min Act: -0.1700

Data Index: 748514 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.3192. Min Act: -0.1700

Data Index: 423543 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.2564. Min Act: -0.1700

Data Index: 1010638 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.2564. Min Act: -0.1700

Data Index: 1078074 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.2878. Min Act: -0.1700

Data Index: 933045 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.2250. Min Act: -0.1700

Data Index: 495890 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.1778. Min Act: -0.1700

Data Index: 583969 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.2250. Min Act: -0.1700

Data Index: 60980 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.2564. Min Act: -0.1700

Data Index: 511554 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.2250. Min Act: -0.1700

Data Index: 313577 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.1935. Min Act: -0.1700

Data Index: 327899 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.2092. Min Act: -0.1700

Data Index: 777638 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 3.4761. Min Range: -3.4761

Max Act: 3.2250. Min Act: -0.1700

Data Index: 878307 (C4 (Web Text))

Max Activating Token Index: 841