Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2618 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0931. Min Range: -4.0931
Max Act: 4.0931. Min Act: -0.1700
Data Index: 12466 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.9681. Min Act: -0.1700
Data Index: 3944477 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.9368. Min Act: -0.1700
Data Index: 1590131 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.8586. Min Act: -0.1700
Data Index: 3596451 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.8899. Min Act: -0.1700
Data Index: 7483304 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.8586. Min Act: -0.1700
Data Index: 8423299 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.8274. Min Act: -0.1700
Data Index: 5343045 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.7961. Min Act: -0.1700
Data Index: 4605540 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.7805. Min Act: -0.1700
Data Index: 3596454 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.7805. Min Act: -0.1700
Data Index: 4648404 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.7805. Min Act: -0.1700
Data Index: 2078885 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.7648. Min Act: -0.1700
Data Index: 1049166 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.7805. Min Act: -0.1700
Data Index: 416379 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.7492. Min Act: -0.1700
Data Index: 3596453 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.7492. Min Act: -0.1700
Data Index: 6211643 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.7492. Min Act: -0.1700
Data Index: 416383 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.7335. Min Act: -0.1700
Data Index: 8082161 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.7648. Min Act: -0.1700
Data Index: 3531647 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.7492. Min Act: -0.1700
Data Index: 3596452 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0931. Min Range: -4.0931
Max Act: 3.7335. Min Act: -0.1700
Data Index: 3076619 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19