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

Dataset: Open Web Text

Neuron 261 in Layer 6

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: 3.4085. Min Range: -3.4085

Max Act: 3.4085. Min Act: -0.1700

Data Index: 6376497 (Open Web Text)

Max Activating Token Index: 1017

Text #1

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3704. Min Act: -0.1700

Data Index: 196942 (Open Web Text)

Max Activating Token Index: 332

Text #2

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3783. Min Act: -0.1700

Data Index: 3245553 (Open Web Text)

Max Activating Token Index: 771

Text #3

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2970. Min Act: -0.1700

Data Index: 5117658 (Open Web Text)

Max Activating Token Index: 340

Text #4

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2925. Min Act: -0.1700

Data Index: 1333163 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.3132. Min Act: -0.1700

Data Index: 4796527 (Open Web Text)

Max Activating Token Index: 293

Text #6

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2835. Min Act: -0.1700

Data Index: 4137887 (Open Web Text)

Max Activating Token Index: 707

Text #7

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2574. Min Act: -0.1700

Data Index: 8276220 (Open Web Text)

Max Activating Token Index: 611

Text #8

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2490. Min Act: -0.1700

Data Index: 1611612 (Open Web Text)

Max Activating Token Index: 213

Text #9

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2294. Min Act: -0.1700

Data Index: 778228 (Open Web Text)

Max Activating Token Index: 489

Text #10

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2601. Min Act: -0.1700

Data Index: 5000175 (Open Web Text)

Max Activating Token Index: 736

Text #11

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2479. Min Act: -0.1700

Data Index: 3213200 (Open Web Text)

Max Activating Token Index: 453

Text #12

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2189. Min Act: -0.1700

Data Index: 7731764 (Open Web Text)

Max Activating Token Index: 124

Text #13

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2087. Min Act: -0.1700

Data Index: 5882331 (Open Web Text)

Max Activating Token Index: 264

Text #14

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2085. Min Act: -0.1700

Data Index: 6714296 (Open Web Text)

Max Activating Token Index: 366

Text #15

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2219. Min Act: -0.1700

Data Index: 5231977 (Open Web Text)

Max Activating Token Index: 349

Text #16

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.2141. Min Act: -0.1700

Data Index: 6865443 (Open Web Text)

Max Activating Token Index: 752

Text #17

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.1988. Min Act: -0.1700

Data Index: 6175033 (Open Web Text)

Max Activating Token Index: 141

Text #18

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.1918. Min Act: -0.1700

Data Index: 1758221 (Open Web Text)

Max Activating Token Index: 379

Text #19

Max Range: 3.4085. Min Range: -3.4085

Max Act: 3.1876. Min Act: -0.1700

Data Index: 8180569 (Open Web Text)

Max Activating Token Index: 514