Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2842 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1695. Min Range: -7.1695
Max Act: 7.1695. Min Act: -0.1700
Data Index: 900323 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.5133. Min Act: -0.1700
Data Index: 6830603 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.5133. Min Act: -0.1700
Data Index: 1619097 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.4195. Min Act: -0.1700
Data Index: 3069822 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.4195. Min Act: -0.1700
Data Index: 8207415 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.4195. Min Act: -0.1700
Data Index: 3013805 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.4195. Min Act: -0.1700
Data Index: 1445082 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.3570. Min Act: -0.1700
Data Index: 5216223 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.3258. Min Act: -0.1700
Data Index: 2417078 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.3258. Min Act: -0.1700
Data Index: 1229548 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.3258. Min Act: -0.1700
Data Index: 1431769 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.2945. Min Act: -0.1700
Data Index: 7736888 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.3258. Min Act: -0.1700
Data Index: 3390592 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.2633. Min Act: -0.1700
Data Index: 8079842 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.2320. Min Act: -0.1700
Data Index: 5003638 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.2320. Min Act: -0.1700
Data Index: 3367610 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.2320. Min Act: -0.1700
Data Index: 5494176 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.1070. Min Act: -0.1700
Data Index: 1470991 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.1070. Min Act: -0.1700
Data Index: 1459955 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1695. Min Range: -7.1695
Max Act: 6.1070. Min Act: -0.1700
Data Index: 6880168 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19