Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1400. Min Range: -3.1400
Max Act: 3.1400. Min Act: -0.1700
Data Index: 8282623 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1400. Min Range: -3.1400
Max Act: 3.0297. Min Act: -0.1700
Data Index: 3285694 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.9981. Min Act: -0.1700
Data Index: 4729968 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1400. Min Range: -3.1400
Max Act: 3.0139. Min Act: -0.1700
Data Index: 3170244 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.9348. Min Act: -0.1700
Data Index: 5010711 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.9348. Min Act: -0.1700
Data Index: 3418550 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.8872. Min Act: -0.1700
Data Index: 1147169 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.8714. Min Act: -0.1700
Data Index: 1048372 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.8714. Min Act: -0.1700
Data Index: 8469254 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.8872. Min Act: -0.1700
Data Index: 4461352 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.8714. Min Act: -0.1700
Data Index: 5647795 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.8555. Min Act: -0.1700
Data Index: 5081783 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.8714. Min Act: -0.1700
Data Index: 2972639 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.8714. Min Act: -0.1700
Data Index: 8501464 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.8555. Min Act: -0.1700
Data Index: 7791843 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.8396. Min Act: -0.1700
Data Index: 8825273 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.8555. Min Act: -0.1700
Data Index: 5599312 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.8396. Min Act: -0.1700
Data Index: 1723807 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.8555. Min Act: -0.1700
Data Index: 5539278 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1400. Min Range: -3.1400
Max Act: 2.8396. Min Act: -0.1700
Data Index: 4554078 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19