Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2454 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.8298. Min Act: -0.1700

Data Index: 8591507 (Open Web Text)

Max Activating Token Index: 922

Text #1

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.8359. Min Act: -0.1700

Data Index: 5889351 (Open Web Text)

Max Activating Token Index: 99

Text #2

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.8206. Min Act: -0.1700

Data Index: 5823227 (Open Web Text)

Max Activating Token Index: 373

Text #3

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.8137. Min Act: -0.1700

Data Index: 407098 (Open Web Text)

Max Activating Token Index: 421

Text #4

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7796. Min Act: -0.1700

Data Index: 113423 (Open Web Text)

Max Activating Token Index: 576

Text #5

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7910. Min Act: -0.1700

Data Index: 5872807 (Open Web Text)

Max Activating Token Index: 152

Text #6

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7767. Min Act: -0.1700

Data Index: 5028398 (Open Web Text)

Max Activating Token Index: 279

Text #7

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7880. Min Act: -0.1700

Data Index: 429061 (Open Web Text)

Max Activating Token Index: 328

Text #8

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7595. Min Act: -0.1700

Data Index: 1440556 (Open Web Text)

Max Activating Token Index: 77

Text #9

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7493. Min Act: -0.1700

Data Index: 4418203 (Open Web Text)

Max Activating Token Index: 168

Text #10

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7449. Min Act: -0.1700

Data Index: 5921641 (Open Web Text)

Max Activating Token Index: 299

Text #11

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7314. Min Act: -0.1700

Data Index: 332077 (Open Web Text)

Max Activating Token Index: 957

Text #12

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7489. Min Act: -0.1700

Data Index: 5378792 (Open Web Text)

Max Activating Token Index: 734

Text #13

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7400. Min Act: -0.1700

Data Index: 2753780 (Open Web Text)

Max Activating Token Index: 144

Text #14

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7408. Min Act: -0.1700

Data Index: 4499335 (Open Web Text)

Max Activating Token Index: 171

Text #15

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7336. Min Act: -0.1700

Data Index: 7228719 (Open Web Text)

Max Activating Token Index: 185

Text #16

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7340. Min Act: -0.1700

Data Index: 7060256 (Open Web Text)

Max Activating Token Index: 820

Text #17

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7243. Min Act: -0.1700

Data Index: 3239166 (Open Web Text)

Max Activating Token Index: 940

Text #18

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7338. Min Act: -0.1700

Data Index: 1288394 (Open Web Text)

Max Activating Token Index: 782

Text #19

Max Range: 1.8359. Min Range: -1.8359

Max Act: 1.7160. Min Act: -0.1700

Data Index: 7320518 (Open Web Text)

Max Activating Token Index: 18