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

Dataset: Open Web Text

Neuron 2436 in Layer 3

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: 3.4933. Min Range: -3.4933

Max Act: 3.4933. Min Act: -0.1700

Data Index: 7077053 (Open Web Text)

Max Activating Token Index: 959

Text #1

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.4359. Min Act: -0.1700

Data Index: 6913918 (Open Web Text)

Max Activating Token Index: 403

Text #2

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.4361. Min Act: -0.1700

Data Index: 261607 (Open Web Text)

Max Activating Token Index: 218

Text #3

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.3686. Min Act: -0.1700

Data Index: 4091271 (Open Web Text)

Max Activating Token Index: 81

Text #4

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.3650. Min Act: -0.1700

Data Index: 5045259 (Open Web Text)

Max Activating Token Index: 445

Text #5

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.3346. Min Act: -0.1700

Data Index: 7808784 (Open Web Text)

Max Activating Token Index: 113

Text #6

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.3388. Min Act: -0.1700

Data Index: 2424614 (Open Web Text)

Max Activating Token Index: 856

Text #7

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.3154. Min Act: -0.1700

Data Index: 5830105 (Open Web Text)

Max Activating Token Index: 813

Text #8

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.3267. Min Act: -0.1700

Data Index: 3414484 (Open Web Text)

Max Activating Token Index: 283

Text #9

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2975. Min Act: -0.1700

Data Index: 3935995 (Open Web Text)

Max Activating Token Index: 968

Text #10

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.3051. Min Act: -0.1700

Data Index: 5538540 (Open Web Text)

Max Activating Token Index: 964

Text #11

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2791. Min Act: -0.1700

Data Index: 5935724 (Open Web Text)

Max Activating Token Index: 231

Text #12

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2867. Min Act: -0.1700

Data Index: 6191873 (Open Web Text)

Max Activating Token Index: 993

Text #13

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2883. Min Act: -0.1700

Data Index: 5640929 (Open Web Text)

Max Activating Token Index: 508

Text #14

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2691. Min Act: -0.1700

Data Index: 4278955 (Open Web Text)

Max Activating Token Index: 124

Text #15

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2578. Min Act: -0.1700

Data Index: 3368924 (Open Web Text)

Max Activating Token Index: 151

Text #16

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2845. Min Act: -0.1700

Data Index: 8340405 (Open Web Text)

Max Activating Token Index: 92

Text #17

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2514. Min Act: -0.1700

Data Index: 3441620 (Open Web Text)

Max Activating Token Index: 130

Text #18

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2608. Min Act: -0.1700

Data Index: 5641204 (Open Web Text)

Max Activating Token Index: 365

Text #19

Max Range: 3.4933. Min Range: -3.4933

Max Act: 3.2444. Min Act: -0.1700

Data Index: 4561576 (Open Web Text)

Max Activating Token Index: 532