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

Dataset: Open Web Text

Neuron 1356 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: 4.6711. Min Range: -4.6711

Max Act: 4.6711. Min Act: -0.1700

Data Index: 5445958 (Open Web Text)

Max Activating Token Index: 314

Text #1

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.6399. Min Act: -0.1700

Data Index: 3352466 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.5049. Min Act: -0.1700

Data Index: 7575462 (Open Web Text)

Max Activating Token Index: 96

Text #3

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.5217. Min Act: -0.1700

Data Index: 4840604 (Open Web Text)

Max Activating Token Index: 107

Text #4

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.5085. Min Act: -0.1700

Data Index: 6259114 (Open Web Text)

Max Activating Token Index: 357

Text #5

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.4669. Min Act: -0.1700

Data Index: 1504935 (Open Web Text)

Max Activating Token Index: 873

Text #6

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.4693. Min Act: -0.1700

Data Index: 4576023 (Open Web Text)

Max Activating Token Index: 82

Text #7

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.4760. Min Act: -0.1700

Data Index: 3016813 (Open Web Text)

Max Activating Token Index: 74

Text #8

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.4653. Min Act: -0.1700

Data Index: 2270778 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.4435. Min Act: -0.1700

Data Index: 3254292 (Open Web Text)

Max Activating Token Index: 27

Text #10

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.4511. Min Act: -0.1700

Data Index: 3216159 (Open Web Text)

Max Activating Token Index: 55

Text #11

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.4638. Min Act: -0.1700

Data Index: 2567841 (Open Web Text)

Max Activating Token Index: 42

Text #12

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.4537. Min Act: -0.1700

Data Index: 278247 (Open Web Text)

Max Activating Token Index: 433

Text #13

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.4442. Min Act: -0.1700

Data Index: 5143683 (Open Web Text)

Max Activating Token Index: 68

Text #14

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.4165. Min Act: -0.1700

Data Index: 4069636 (Open Web Text)

Max Activating Token Index: 186

Text #15

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.4164. Min Act: -0.1700

Data Index: 3967929 (Open Web Text)

Max Activating Token Index: 134

Text #16

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.4154. Min Act: -0.1700

Data Index: 3625661 (Open Web Text)

Max Activating Token Index: 29

Text #17

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.4173. Min Act: -0.1700

Data Index: 5543323 (Open Web Text)

Max Activating Token Index: 45

Text #18

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.3997. Min Act: -0.1700

Data Index: 3761592 (Open Web Text)

Max Activating Token Index: 181

Text #19

Max Range: 4.6711. Min Range: -4.6711

Max Act: 4.4361. Min Act: -0.1700

Data Index: 5796072 (Open Web Text)

Max Activating Token Index: 90