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

Dataset: Open Web Text

Neuron 2968 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: 1.8986. Min Range: -1.8986

Max Act: 1.8986. Min Act: -0.1700

Data Index: 5223965 (Open Web Text)

Max Activating Token Index: 144

Text #1

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8788. Min Act: -0.1700

Data Index: 3490864 (Open Web Text)

Max Activating Token Index: 82

Text #2

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8825. Min Act: -0.1700

Data Index: 2431243 (Open Web Text)

Max Activating Token Index: 65

Text #3

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8817. Min Act: -0.1700

Data Index: 3256299 (Open Web Text)

Max Activating Token Index: 337

Text #4

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8635. Min Act: -0.1700

Data Index: 12745 (Open Web Text)

Max Activating Token Index: 98

Text #5

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8628. Min Act: -0.1700

Data Index: 6886790 (Open Web Text)

Max Activating Token Index: 58

Text #6

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8639. Min Act: -0.1700

Data Index: 4873053 (Open Web Text)

Max Activating Token Index: 179

Text #7

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8553. Min Act: -0.1700

Data Index: 1239129 (Open Web Text)

Max Activating Token Index: 126

Text #8

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8551. Min Act: -0.1700

Data Index: 6525364 (Open Web Text)

Max Activating Token Index: 74

Text #9

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8613. Min Act: -0.1700

Data Index: 4199732 (Open Web Text)

Max Activating Token Index: 226

Text #10

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8472. Min Act: -0.1700

Data Index: 6428019 (Open Web Text)

Max Activating Token Index: 229

Text #11

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8432. Min Act: -0.1700

Data Index: 7364732 (Open Web Text)

Max Activating Token Index: 195

Text #12

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8376. Min Act: -0.1700

Data Index: 4138049 (Open Web Text)

Max Activating Token Index: 45

Text #13

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8366. Min Act: -0.1700

Data Index: 2010582 (Open Web Text)

Max Activating Token Index: 91

Text #14

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8435. Min Act: -0.1700

Data Index: 6744367 (Open Web Text)

Max Activating Token Index: 126

Text #15

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8330. Min Act: -0.1700

Data Index: 5591542 (Open Web Text)

Max Activating Token Index: 81

Text #16

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8332. Min Act: -0.1700

Data Index: 6540924 (Open Web Text)

Max Activating Token Index: 876

Text #17

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8202. Min Act: -0.1700

Data Index: 971589 (Open Web Text)

Max Activating Token Index: 373

Text #18

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8154. Min Act: -0.1700

Data Index: 6895436 (Open Web Text)

Max Activating Token Index: 454

Text #19

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8212. Min Act: -0.1700

Data Index: 2255015 (Open Web Text)

Max Activating Token Index: 161