Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2390 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.9437. Min Act: -0.1700
Data Index: 4336476 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.7874. Min Act: -0.1700
Data Index: 3066083 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.7249. Min Act: -0.1700
Data Index: 1761623 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.6624. Min Act: -0.1700
Data Index: 8464951 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.6624. Min Act: -0.1700
Data Index: 3851181 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.6624. Min Act: -0.1700
Data Index: 860426 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.5999. Min Act: -0.1700
Data Index: 225504 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.5374. Min Act: -0.1700
Data Index: 530511 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.5999. Min Act: -0.1700
Data Index: 4122076 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.5687. Min Act: -0.1700
Data Index: 8129259 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.5687. Min Act: -0.1700
Data Index: 5459911 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.5999. Min Act: -0.1700
Data Index: 449609 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.5687. Min Act: -0.1700
Data Index: 2586057 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.5374. Min Act: -0.1700
Data Index: 7884227 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.5687. Min Act: -0.1700
Data Index: 7060562 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.5687. Min Act: -0.1700
Data Index: 6192135 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.5687. Min Act: -0.1700
Data Index: 4023063 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.5374. Min Act: -0.1700
Data Index: 5448726 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.5374. Min Act: -0.1700
Data Index: 4906425 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9437. Min Range: -5.9437
Max Act: 5.5062. Min Act: -0.1700
Data Index: 8384084 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19