Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 200 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3573. Min Range: -6.3573
Max Act: 6.3573. Min Act: -0.1700
Data Index: 4259680 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3573. Min Range: -6.3573
Max Act: 6.2636. Min Act: -0.1700
Data Index: 6571836 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3573. Min Range: -6.3573
Max Act: 6.0448. Min Act: -0.1700
Data Index: 6952856 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.9823. Min Act: -0.1700
Data Index: 994332 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.9511. Min Act: -0.1700
Data Index: 7399278 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.8573. Min Act: -0.1700
Data Index: 8163445 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.8573. Min Act: -0.1700
Data Index: 5088389 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.8573. Min Act: -0.1700
Data Index: 830102 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.7323. Min Act: -0.1700
Data Index: 4326642 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.6698. Min Act: -0.1700
Data Index: 6952855 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.6698. Min Act: -0.1700
Data Index: 997428 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.6698. Min Act: -0.1700
Data Index: 4582488 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.6698. Min Act: -0.1700
Data Index: 1977439 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.6386. Min Act: -0.1700
Data Index: 3503304 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.6073. Min Act: -0.1700
Data Index: 5028008 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.6386. Min Act: -0.1700
Data Index: 6975458 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.6386. Min Act: -0.1700
Data Index: 8704302 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.6386. Min Act: -0.1700
Data Index: 5550369 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.5761. Min Act: -0.1700
Data Index: 4438222 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3573. Min Range: -6.3573
Max Act: 5.5761. Min Act: -0.1700
Data Index: 7039666 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19