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

Dataset: Open Web Text

Neuron 310 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: 5.4369. Min Range: -5.4369

Max Act: 5.4369. Min Act: -0.1700

Data Index: 147250 (Open Web Text)

Max Activating Token Index: 1002

Text #1

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.4093. Min Act: -0.1700

Data Index: 8438538 (Open Web Text)

Max Activating Token Index: 423

Text #2

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.4057. Min Act: -0.1700

Data Index: 1476256 (Open Web Text)

Max Activating Token Index: 38

Text #3

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3763. Min Act: -0.1700

Data Index: 7984580 (Open Web Text)

Max Activating Token Index: 922

Text #4

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3463. Min Act: -0.1700

Data Index: 4948783 (Open Web Text)

Max Activating Token Index: 193

Text #5

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3388. Min Act: -0.1700

Data Index: 5094447 (Open Web Text)

Max Activating Token Index: 229

Text #6

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3493. Min Act: -0.1700

Data Index: 5289059 (Open Web Text)

Max Activating Token Index: 409

Text #7

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3630. Min Act: -0.1700

Data Index: 6577599 (Open Web Text)

Max Activating Token Index: 106

Text #8

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3409. Min Act: -0.1700

Data Index: 1051224 (Open Web Text)

Max Activating Token Index: 143

Text #9

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3273. Min Act: -0.1700

Data Index: 1844844 (Open Web Text)

Max Activating Token Index: 393

Text #10

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3390. Min Act: -0.1700

Data Index: 2457414 (Open Web Text)

Max Activating Token Index: 1010

Text #11

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3295. Min Act: -0.1700

Data Index: 4491992 (Open Web Text)

Max Activating Token Index: 284

Text #12

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3121. Min Act: -0.1700

Data Index: 5688162 (Open Web Text)

Max Activating Token Index: 326

Text #13

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3109. Min Act: -0.1700

Data Index: 5904119 (Open Web Text)

Max Activating Token Index: 476

Text #14

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3083. Min Act: -0.1700

Data Index: 2956981 (Open Web Text)

Max Activating Token Index: 1017

Text #15

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3214. Min Act: -0.1700

Data Index: 3177817 (Open Web Text)

Max Activating Token Index: 979

Text #16

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3361. Min Act: -0.1700

Data Index: 1716906 (Open Web Text)

Max Activating Token Index: 956

Text #17

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3188. Min Act: -0.1700

Data Index: 7757016 (Open Web Text)

Max Activating Token Index: 1015

Text #18

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3129. Min Act: -0.1700

Data Index: 3347719 (Open Web Text)

Max Activating Token Index: 125

Text #19

Max Range: 5.4369. Min Range: -5.4369

Max Act: 5.3214. Min Act: -0.1700

Data Index: 1621259 (Open Web Text)

Max Activating Token Index: 1021