Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3319 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.2731. Min Act: -0.1700
Data Index: 6144439 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.2106. Min Act: -0.1700
Data Index: 3317784 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.2106. Min Act: -0.1700
Data Index: 2973320 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.2106. Min Act: -0.1700
Data Index: 6955148 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.1793. Min Act: -0.1700
Data Index: 6990505 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.1793. Min Act: -0.1700
Data Index: 5397268 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.1481. Min Act: -0.1700
Data Index: 1734232 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.1481. Min Act: -0.1700
Data Index: 2841358 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.1481. Min Act: -0.1700
Data Index: 4889011 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.1168. Min Act: -0.1700
Data Index: 7080321 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.1481. Min Act: -0.1700
Data Index: 5566651 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.1168. Min Act: -0.1700
Data Index: 3164537 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.1168. Min Act: -0.1700
Data Index: 3954315 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.1168. Min Act: -0.1700
Data Index: 4647757 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.1481. Min Act: -0.1700
Data Index: 4107582 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.0543. Min Act: -0.1700
Data Index: 960585 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.0856. Min Act: -0.1700
Data Index: 97425 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.1168. Min Act: -0.1700
Data Index: 4312588 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.1168. Min Act: -0.1700
Data Index: 4976064 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2731. Min Range: -5.2731
Max Act: 5.1168. Min Act: -0.1700
Data Index: 2966689 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19