Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4807 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3745. Min Range: -6.3745
Max Act: 6.3745. Min Act: -0.1700
Data Index: 1365081 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3745. Min Range: -6.3745
Max Act: 6.3120. Min Act: -0.1700
Data Index: 3724181 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3745. Min Range: -6.3745
Max Act: 6.1557. Min Act: -0.1700
Data Index: 829303 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3745. Min Range: -6.3745
Max Act: 6.0932. Min Act: -0.1700
Data Index: 463465 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.9370. Min Act: -0.1700
Data Index: 7618678 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.9057. Min Act: -0.1700
Data Index: 4580527 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.9057. Min Act: -0.1700
Data Index: 8789756 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.8120. Min Act: -0.1700
Data Index: 7730474 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.7807. Min Act: -0.1700
Data Index: 5169314 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.7182. Min Act: -0.1700
Data Index: 1609265 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.6870. Min Act: -0.1700
Data Index: 7751604 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.6870. Min Act: -0.1700
Data Index: 5770169 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.6557. Min Act: -0.1700
Data Index: 214426 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.6245. Min Act: -0.1700
Data Index: 3901468 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.6557. Min Act: -0.1700
Data Index: 3178320 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.6245. Min Act: -0.1700
Data Index: 2936569 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.5620. Min Act: -0.1700
Data Index: 8295328 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.5307. Min Act: -0.1700
Data Index: 7384283 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.5620. Min Act: -0.1700
Data Index: 7894342 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3745. Min Range: -6.3745
Max Act: 5.5307. Min Act: -0.1700
Data Index: 1503625 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19