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

Dataset: Open Web Text

Neuron 93 in Layer 0

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: 1.3593. Min Range: -1.3593

Max Act: 1.3593. Min Act: -0.1083

Data Index: 7611537 (Open Web Text)

Max Activating Token Index: 256

Text #1

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.3003. Min Act: -0.1048

Data Index: 6701633 (Open Web Text)

Max Activating Token Index: 597

Text #2

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2754. Min Act: -0.1360

Data Index: 6909675 (Open Web Text)

Max Activating Token Index: 248

Text #3

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2733. Min Act: -0.1164

Data Index: 7882948 (Open Web Text)

Max Activating Token Index: 169

Text #4

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2664. Min Act: -0.1518

Data Index: 3146667 (Open Web Text)

Max Activating Token Index: 672

Text #5

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2590. Min Act: -0.0831

Data Index: 1007545 (Open Web Text)

Max Activating Token Index: 95

Text #6

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2688. Min Act: -0.1091

Data Index: 7415500 (Open Web Text)

Max Activating Token Index: 804

Text #7

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2628. Min Act: -0.0766

Data Index: 6639091 (Open Web Text)

Max Activating Token Index: 236

Text #8

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2664. Min Act: -0.1119

Data Index: 6679749 (Open Web Text)

Max Activating Token Index: 160

Text #9

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2589. Min Act: -0.1679

Data Index: 6705973 (Open Web Text)

Max Activating Token Index: 272

Text #10

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2587. Min Act: -0.1270

Data Index: 4728269 (Open Web Text)

Max Activating Token Index: 363

Text #11

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2532. Min Act: -0.0791

Data Index: 5688669 (Open Web Text)

Max Activating Token Index: 413

Text #12

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2545. Min Act: -0.0455

Data Index: 2765432 (Open Web Text)

Max Activating Token Index: 635

Text #13

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2475. Min Act: -0.1136

Data Index: 1478800 (Open Web Text)

Max Activating Token Index: 96

Text #14

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2504. Min Act: -0.0750

Data Index: 5592361 (Open Web Text)

Max Activating Token Index: 248

Text #15

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2477. Min Act: -0.1091

Data Index: 2127033 (Open Web Text)

Max Activating Token Index: 447

Text #16

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2479. Min Act: -0.1628

Data Index: 7729923 (Open Web Text)

Max Activating Token Index: 208

Text #17

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2418. Min Act: -0.0868

Data Index: 6566788 (Open Web Text)

Max Activating Token Index: 458

Text #18

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2447. Min Act: -0.0709

Data Index: 5893140 (Open Web Text)

Max Activating Token Index: 795

Text #19

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2435. Min Act: -0.1470

Data Index: 3106481 (Open Web Text)

Max Activating Token Index: 83