Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 49 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0370. Min Range: -5.0370
Max Act: 5.0370. Min Act: -0.1700
Data Index: 3717872 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.9433. Min Act: -0.1700
Data Index: 4322456 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8808. Min Act: -0.1700
Data Index: 2113463 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8495. Min Act: -0.1700
Data Index: 5054937 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8495. Min Act: -0.1700
Data Index: 3623230 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.8495. Min Act: -0.1700
Data Index: 2895402 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.7870. Min Act: -0.1700
Data Index: 2465026 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.7558. Min Act: -0.1700
Data Index: 5946672 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.7870. Min Act: -0.1700
Data Index: 5772675 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.7870. Min Act: -0.1700
Data Index: 8082277 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.7245. Min Act: -0.1700
Data Index: 3842271 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.7245. Min Act: -0.1700
Data Index: 2969412 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.7245. Min Act: -0.1700
Data Index: 6491270 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.6933. Min Act: -0.1700
Data Index: 185193 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.6933. Min Act: -0.1700
Data Index: 5775067 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.6620. Min Act: -0.1700
Data Index: 5090821 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.6620. Min Act: -0.1700
Data Index: 1161872 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.6308. Min Act: -0.1700
Data Index: 5113814 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.6620. Min Act: -0.1700
Data Index: 6797318 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0370. Min Range: -5.0370
Max Act: 4.6308. Min Act: -0.1700
Data Index: 3047911 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19