Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1293 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4109. Min Range: -8.4109
Max Act: 8.4109. Min Act: -0.1700
Data Index: 2332469 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4109. Min Range: -8.4109
Max Act: 8.4109. Min Act: -0.1700
Data Index: 8507159 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4109. Min Range: -8.4109
Max Act: 8.2859. Min Act: -0.1700
Data Index: 2471637 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4109. Min Range: -8.4109
Max Act: 8.0984. Min Act: -0.1700
Data Index: 2797798 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4109. Min Range: -8.4109
Max Act: 8.0984. Min Act: -0.1700
Data Index: 4700067 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4109. Min Range: -8.4109
Max Act: 8.0359. Min Act: -0.1700
Data Index: 1797896 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4109. Min Range: -8.4109
Max Act: 7.9734. Min Act: -0.1700
Data Index: 5570515 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4109. Min Range: -8.4109
Max Act: 8.0984. Min Act: -0.1700
Data Index: 7317055 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4109. Min Range: -8.4109
Max Act: 7.9734. Min Act: -0.1700
Data Index: 128163 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4109. Min Range: -8.4109
Max Act: 7.9109. Min Act: -0.1700
Data Index: 5201453 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4109. Min Range: -8.4109
Max Act: 7.8484. Min Act: -0.1700
Data Index: 3187911 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4109. Min Range: -8.4109
Max Act: 7.7859. Min Act: -0.1700
Data Index: 7084626 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4109. Min Range: -8.4109
Max Act: 7.8484. Min Act: -0.1700
Data Index: 4253848 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4109. Min Range: -8.4109
Max Act: 7.7859. Min Act: -0.1700
Data Index: 4892749 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4109. Min Range: -8.4109
Max Act: 7.8484. Min Act: -0.1700
Data Index: 7356799 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4109. Min Range: -8.4109
Max Act: 7.8484. Min Act: -0.1700
Data Index: 6677027 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4109. Min Range: -8.4109
Max Act: 7.7859. Min Act: -0.1700
Data Index: 8382165 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4109. Min Range: -8.4109
Max Act: 7.8484. Min Act: -0.1700
Data Index: 2686395 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4109. Min Range: -8.4109
Max Act: 7.7859. Min Act: -0.1700
Data Index: 966673 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4109. Min Range: -8.4109
Max Act: 7.7859. Min Act: -0.1700
Data Index: 2016206 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19