Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2494 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6833. Min Range: -7.6833
Max Act: 7.6833. Min Act: -0.1700
Data Index: 7011811 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6833. Min Range: -7.6833
Max Act: 7.5895. Min Act: -0.1700
Data Index: 6816975 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6833. Min Range: -7.6833
Max Act: 7.3395. Min Act: -0.1700
Data Index: 7611095 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6833. Min Range: -7.6833
Max Act: 7.3083. Min Act: -0.1700
Data Index: 134072 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6833. Min Range: -7.6833
Max Act: 7.2145. Min Act: -0.1700
Data Index: 4598230 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6833. Min Range: -7.6833
Max Act: 7.2145. Min Act: -0.1700
Data Index: 4718330 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6833. Min Range: -7.6833
Max Act: 7.1833. Min Act: -0.1700
Data Index: 962293 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6833. Min Range: -7.6833
Max Act: 7.0895. Min Act: -0.1700
Data Index: 2860178 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6833. Min Range: -7.6833
Max Act: 7.0270. Min Act: -0.1700
Data Index: 7697960 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6833. Min Range: -7.6833
Max Act: 6.9958. Min Act: -0.1700
Data Index: 696937 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6833. Min Range: -7.6833
Max Act: 6.9958. Min Act: -0.1700
Data Index: 7289047 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6833. Min Range: -7.6833
Max Act: 6.9958. Min Act: -0.1700
Data Index: 5495381 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6833. Min Range: -7.6833
Max Act: 6.9958. Min Act: -0.1700
Data Index: 1661443 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6833. Min Range: -7.6833
Max Act: 6.9645. Min Act: -0.1700
Data Index: 1362308 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6833. Min Range: -7.6833
Max Act: 6.9958. Min Act: -0.1700
Data Index: 1041656 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6833. Min Range: -7.6833
Max Act: 6.9645. Min Act: -0.1700
Data Index: 2422890 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6833. Min Range: -7.6833
Max Act: 6.9333. Min Act: -0.1700
Data Index: 3107446 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6833. Min Range: -7.6833
Max Act: 6.9333. Min Act: -0.1700
Data Index: 6053480 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6833. Min Range: -7.6833
Max Act: 6.9020. Min Act: -0.1700
Data Index: 4821054 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6833. Min Range: -7.6833
Max Act: 6.8708. Min Act: -0.1700
Data Index: 7129782 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19