Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2421 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.7507. Min Act: -0.1700
Data Index: 5076684 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.6257. Min Act: -0.1700
Data Index: 5271412 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5320. Min Act: -0.1700
Data Index: 4975673 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5007. Min Act: -0.1700
Data Index: 6612456 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4695. Min Act: -0.1700
Data Index: 2784760 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4695. Min Act: -0.1700
Data Index: 4422019 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4695. Min Act: -0.1700
Data Index: 7969088 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3757. Min Act: -0.1700
Data Index: 3701459 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3757. Min Act: -0.1700
Data Index: 5298860 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3132. Min Act: -0.1700
Data Index: 6214820 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2820. Min Act: -0.1700
Data Index: 7810346 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2820. Min Act: -0.1700
Data Index: 5390223 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.3132. Min Act: -0.1700
Data Index: 1092424 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2507. Min Act: -0.1700
Data Index: 5572850 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2820. Min Act: -0.1700
Data Index: 1544081 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2820. Min Act: -0.1700
Data Index: 6236920 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2507. Min Act: -0.1700
Data Index: 8008371 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2507. Min Act: -0.1700
Data Index: 7515824 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2507. Min Act: -0.1700
Data Index: 3193705 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.2507. Min Act: -0.1700
Data Index: 926032 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19