Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4004 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.9500. Min Act: -0.1700
Data Index: 6028058 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.7000. Min Act: -0.1700
Data Index: 2809233 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.6688. Min Act: -0.1700
Data Index: 3691290 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.6063. Min Act: -0.1700
Data Index: 8331574 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.6063. Min Act: -0.1700
Data Index: 7545784 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.5125. Min Act: -0.1700
Data Index: 7887494 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.5125. Min Act: -0.1700
Data Index: 3433574 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.4813. Min Act: -0.1700
Data Index: 973008 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.5125. Min Act: -0.1700
Data Index: 6887448 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.4188. Min Act: -0.1700
Data Index: 4698573 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.4500. Min Act: -0.1700
Data Index: 6903199 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.4500. Min Act: -0.1700
Data Index: 2637800 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.4188. Min Act: -0.1700
Data Index: 6200541 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.4188. Min Act: -0.1700
Data Index: 94474 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.4188. Min Act: -0.1700
Data Index: 3401208 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.3563. Min Act: -0.1700
Data Index: 6809320 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.3875. Min Act: -0.1700
Data Index: 1373275 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.4188. Min Act: -0.1700
Data Index: 1399246 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.3875. Min Act: -0.1700
Data Index: 1687094 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9500. Min Range: -4.9500
Max Act: 4.3875. Min Act: -0.1700
Data Index: 5601377 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19