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

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

Neuron 1398 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: 5.3942. Min Range: -5.3942

Max Act: 5.3942. Min Act: -0.1700

Data Index: 987775 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 5.3942. Min Range: -5.3942

Max Act: 5.3942. Min Act: -0.1700

Data Index: 1081003 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 5.3942. Min Range: -5.3942

Max Act: 5.3005. Min Act: -0.1700

Data Index: 1129780 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 5.3942. Min Range: -5.3942

Max Act: 5.3317. Min Act: -0.1700

Data Index: 26816 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 5.3942. Min Range: -5.3942

Max Act: 5.2692. Min Act: -0.1700

Data Index: 1304710 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 5.3942. Min Range: -5.3942

Max Act: 5.3005. Min Act: -0.1700

Data Index: 1222679 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 5.3942. Min Range: -5.3942

Max Act: 5.2692. Min Act: -0.1700

Data Index: 572169 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 5.3942. Min Range: -5.3942

Max Act: 5.2692. Min Act: -0.1700

Data Index: 1120337 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 5.3942. Min Range: -5.3942

Max Act: 5.2380. Min Act: -0.1700

Data Index: 119802 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 5.3942. Min Range: -5.3942

Max Act: 5.1755. Min Act: -0.1700

Data Index: 725028 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 5.3942. Min Range: -5.3942

Max Act: 5.1130. Min Act: -0.1699

Data Index: 1255011 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 5.3942. Min Range: -5.3942

Max Act: 5.0505. Min Act: -0.1700

Data Index: 1247958 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 5.3942. Min Range: -5.3942

Max Act: 5.0817. Min Act: -0.1700

Data Index: 1341429 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 5.3942. Min Range: -5.3942

Max Act: 4.9880. Min Act: -0.1700

Data Index: 716990 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 5.3942. Min Range: -5.3942

Max Act: 4.9880. Min Act: -0.1700

Data Index: 91908 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 5.3942. Min Range: -5.3942

Max Act: 5.0192. Min Act: -0.1700

Data Index: 736260 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 5.3942. Min Range: -5.3942

Max Act: 4.9880. Min Act: -0.1700

Data Index: 878655 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 5.3942. Min Range: -5.3942

Max Act: 4.9880. Min Act: -0.1700

Data Index: 784551 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 5.3942. Min Range: -5.3942

Max Act: 4.9567. Min Act: -0.1700

Data Index: 252732 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 5.3942. Min Range: -5.3942

Max Act: 4.9880. Min Act: -0.1700

Data Index: 100250 (C4 (Web Text))

Max Activating Token Index: 71