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

Dataset: Open Web Text

Neuron 3030 in Layer 4

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: 3.3942. Min Range: -3.3942

Max Act: 3.3942. Min Act: -0.1700

Data Index: 4023232 (Open Web Text)

Max Activating Token Index: 299

Text #1

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2783. Min Act: -0.1700

Data Index: 4761576 (Open Web Text)

Max Activating Token Index: 118

Text #2

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2690. Min Act: -0.1700

Data Index: 4743129 (Open Web Text)

Max Activating Token Index: 47

Text #3

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2521. Min Act: -0.1700

Data Index: 2711366 (Open Web Text)

Max Activating Token Index: 149

Text #4

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2437. Min Act: -0.1700

Data Index: 4996090 (Open Web Text)

Max Activating Token Index: 294

Text #5

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2401. Min Act: -0.1700

Data Index: 7790657 (Open Web Text)

Max Activating Token Index: 129

Text #6

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2364. Min Act: -0.1700

Data Index: 2422886 (Open Web Text)

Max Activating Token Index: 386

Text #7

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2163. Min Act: -0.1700

Data Index: 6121317 (Open Web Text)

Max Activating Token Index: 276

Text #8

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2236. Min Act: -0.1700

Data Index: 2554931 (Open Web Text)

Max Activating Token Index: 820

Text #9

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2124. Min Act: -0.1700

Data Index: 7623775 (Open Web Text)

Max Activating Token Index: 638

Text #10

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2316. Min Act: -0.1700

Data Index: 668641 (Open Web Text)

Max Activating Token Index: 269

Text #11

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2044. Min Act: -0.1700

Data Index: 2820451 (Open Web Text)

Max Activating Token Index: 127

Text #12

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1977. Min Act: -0.1700

Data Index: 3965956 (Open Web Text)

Max Activating Token Index: 867

Text #13

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2036. Min Act: -0.1700

Data Index: 8632648 (Open Web Text)

Max Activating Token Index: 882

Text #14

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1980. Min Act: -0.1700

Data Index: 8140628 (Open Web Text)

Max Activating Token Index: 401

Text #15

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1968. Min Act: -0.1700

Data Index: 197422 (Open Web Text)

Max Activating Token Index: 80

Text #16

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.2091. Min Act: -0.1700

Data Index: 3452319 (Open Web Text)

Max Activating Token Index: 255

Text #17

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1565. Min Act: -0.1700

Data Index: 6718920 (Open Web Text)

Max Activating Token Index: 948

Text #18

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1924. Min Act: -0.1700

Data Index: 7444126 (Open Web Text)

Max Activating Token Index: 356

Text #19

Max Range: 3.3942. Min Range: -3.3942

Max Act: 3.1859. Min Act: -0.1700

Data Index: 1328526 (Open Web Text)

Max Activating Token Index: 211