Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1977 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.8440. Min Act: -0.1700

Data Index: 12702 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7814. Min Act: -0.1700

Data Index: 72483 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.7501. Min Act: -0.1700

Data Index: 294507 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.6719. Min Act: -0.1700

Data Index: 431504 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.6249. Min Act: -0.1700

Data Index: 665089 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.6093. Min Act: -0.1700

Data Index: 952029 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.5623. Min Act: -0.1700

Data Index: 384306 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.5153. Min Act: -0.1700

Data Index: 248532 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.5153. Min Act: -0.1700

Data Index: 972876 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.5310. Min Act: -0.1700

Data Index: 1321802 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.4526. Min Act: -0.1700

Data Index: 1309928 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.4369. Min Act: -0.1700

Data Index: 1195654 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.4213. Min Act: -0.1700

Data Index: 891987 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.4526. Min Act: -0.1700

Data Index: 826843 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.4369. Min Act: -0.1700

Data Index: 814961 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.4213. Min Act: -0.1700

Data Index: 1248436 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.4369. Min Act: -0.1700

Data Index: 1064914 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.4683. Min Act: -0.1700

Data Index: 614714 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.4056. Min Act: -0.1700

Data Index: 1069704 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 3.8440. Min Range: -3.8440

Max Act: 3.3742. Min Act: -0.1700

Data Index: 20105 (C4 (Web Text))

Max Activating Token Index: 9