Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5589 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.9809. Min Act: -0.1700
Data Index: 4568180 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.9651. Min Act: -0.1700
Data Index: 3003114 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.9176. Min Act: -0.1700
Data Index: 3396001 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.8859. Min Act: -0.1700
Data Index: 1973674 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.8541. Min Act: -0.1700
Data Index: 1648215 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.8700. Min Act: -0.1700
Data Index: 4999708 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.8700. Min Act: -0.1700
Data Index: 2907075 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.8064. Min Act: -0.1700
Data Index: 5245484 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.7586. Min Act: -0.1700
Data Index: 8627514 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.7745. Min Act: -0.1700
Data Index: 4221622 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.7586. Min Act: -0.1700
Data Index: 5568190 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.7267. Min Act: -0.1700
Data Index: 5178103 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.7426. Min Act: -0.1700
Data Index: 670277 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.7426. Min Act: -0.1700
Data Index: 5466941 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.7267. Min Act: -0.1700
Data Index: 439224 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.7267. Min Act: -0.1700
Data Index: 3940447 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.7267. Min Act: -0.1700
Data Index: 5639064 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.7267. Min Act: -0.1700
Data Index: 983674 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.6947. Min Act: -0.1700
Data Index: 2109058 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9809. Min Range: -2.9809
Max Act: 2.7107. Min Act: -0.1700
Data Index: 4938315 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19