Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 995 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.4397. Min Act: -0.1700

Data Index: 422310 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.3713. Min Act: -0.1700

Data Index: 104717 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.3333. Min Act: -0.1700

Data Index: 538903 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.3408. Min Act: -0.1700

Data Index: 430956 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.3175. Min Act: -0.1700

Data Index: 1173756 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2774. Min Act: -0.1700

Data Index: 692501 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.3042. Min Act: -0.1700

Data Index: 284731 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2780. Min Act: -0.1700

Data Index: 815138 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.3060. Min Act: -0.1700

Data Index: 1068523 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2653. Min Act: -0.1700

Data Index: 986928 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2727. Min Act: -0.1699

Data Index: 71046 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2518. Min Act: -0.1700

Data Index: 811379 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2651. Min Act: -0.1700

Data Index: 1256634 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2708. Min Act: -0.1700

Data Index: 612795 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2676. Min Act: -0.1700

Data Index: 832941 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2217. Min Act: -0.1700

Data Index: 95211 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2437. Min Act: -0.1700

Data Index: 966141 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2255. Min Act: -0.1700

Data Index: 155218 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2234. Min Act: -0.1700

Data Index: 571579 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.2246. Min Act: -0.1700

Data Index: 823031 (C4 (Web Text))

Max Activating Token Index: 372