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

Dataset: Open Web Text

Neuron 1256 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: 7.4457. Min Range: -7.4457

Max Act: 7.4244. Min Act: -0.1700

Data Index: 7359555 (Open Web Text)

Max Activating Token Index: 312

Text #1

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.4457. Min Act: -0.1700

Data Index: 2549793 (Open Web Text)

Max Activating Token Index: 288

Text #2

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.3118. Min Act: -0.1700

Data Index: 2689359 (Open Web Text)

Max Activating Token Index: 401

Text #3

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.2822. Min Act: -0.1700

Data Index: 6578199 (Open Web Text)

Max Activating Token Index: 126

Text #4

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.2699. Min Act: -0.1700

Data Index: 6809002 (Open Web Text)

Max Activating Token Index: 87

Text #5

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.2340. Min Act: -0.1700

Data Index: 7175787 (Open Web Text)

Max Activating Token Index: 108

Text #6

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.2201. Min Act: -0.1700

Data Index: 3125569 (Open Web Text)

Max Activating Token Index: 107

Text #7

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.2071. Min Act: -0.1700

Data Index: 8018097 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.1411. Min Act: -0.1700

Data Index: 4893522 (Open Web Text)

Max Activating Token Index: 120

Text #9

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.1295. Min Act: -0.1700

Data Index: 3169169 (Open Web Text)

Max Activating Token Index: 111

Text #10

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.1575. Min Act: -0.1700

Data Index: 2455930 (Open Web Text)

Max Activating Token Index: 690

Text #11

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.0962. Min Act: -0.1700

Data Index: 296402 (Open Web Text)

Max Activating Token Index: 267

Text #12

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.0717. Min Act: -0.1700

Data Index: 5445337 (Open Web Text)

Max Activating Token Index: 317

Text #13

Max Range: 7.4457. Min Range: -7.4457

Max Act: 6.9850. Min Act: -0.1700

Data Index: 8498715 (Open Web Text)

Max Activating Token Index: 303

Text #14

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.0318. Min Act: -0.1700

Data Index: 3494785 (Open Web Text)

Max Activating Token Index: 138

Text #15

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.0205. Min Act: -0.1700

Data Index: 3305745 (Open Web Text)

Max Activating Token Index: 277

Text #16

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.0191. Min Act: -0.1700

Data Index: 1954536 (Open Web Text)

Max Activating Token Index: 60

Text #17

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.0393. Min Act: -0.1700

Data Index: 7467519 (Open Web Text)

Max Activating Token Index: 591

Text #18

Max Range: 7.4457. Min Range: -7.4457

Max Act: 7.0001. Min Act: -0.1700

Data Index: 5054192 (Open Web Text)

Max Activating Token Index: 133

Text #19

Max Range: 7.4457. Min Range: -7.4457

Max Act: 6.9799. Min Act: -0.1700

Data Index: 2283655 (Open Web Text)

Max Activating Token Index: 263