Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1637 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.6670. Min Act: -0.1700
Data Index: 5133510 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.5420. Min Act: -0.1700
Data Index: 4458456 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.5108. Min Act: -0.1700
Data Index: 7643795 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.5108. Min Act: -0.1700
Data Index: 1241747 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.3858. Min Act: -0.1700
Data Index: 5155804 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.3858. Min Act: -0.1700
Data Index: 7190700 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.3233. Min Act: -0.1700
Data Index: 5176 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.2920. Min Act: -0.1700
Data Index: 278906 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.2608. Min Act: -0.1700
Data Index: 8171549 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.2608. Min Act: -0.1700
Data Index: 627368 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.2295. Min Act: -0.1700
Data Index: 541170 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.1983. Min Act: -0.1700
Data Index: 4246583 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.1670. Min Act: -0.1700
Data Index: 8247852 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.1670. Min Act: -0.1700
Data Index: 7472096 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.1358. Min Act: -0.1700
Data Index: 7326421 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.1670. Min Act: -0.1700
Data Index: 928277 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.1670. Min Act: -0.1700
Data Index: 5504877 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.1045. Min Act: -0.1700
Data Index: 7107041 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.1670. Min Act: -0.1700
Data Index: 1565946 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6670. Min Range: -4.6670
Max Act: 4.1358. Min Act: -0.1700
Data Index: 3433410 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19