Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1984 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.7001. Min Act: -0.1700
Data Index: 5759563 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.7001. Min Act: -0.1700
Data Index: 6365873 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.6689. Min Act: -0.1700
Data Index: 5561590 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.6376. Min Act: -0.1700
Data Index: 4174586 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.6376. Min Act: -0.1700
Data Index: 6412603 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.6376. Min Act: -0.1700
Data Index: 8373193 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.6689. Min Act: -0.1700
Data Index: 7524916 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.6064. Min Act: -0.1700
Data Index: 6101565 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.5751. Min Act: -0.1700
Data Index: 1567791 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.5751. Min Act: -0.1700
Data Index: 7654683 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.5439. Min Act: -0.1700
Data Index: 5758848 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.5126. Min Act: -0.1700
Data Index: 599962 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.5439. Min Act: -0.1700
Data Index: 604793 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.3564. Min Act: -0.1700
Data Index: 8722370 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.3564. Min Act: -0.1700
Data Index: 7172930 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.3564. Min Act: -0.1700
Data Index: 2402160 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.2939. Min Act: -0.1700
Data Index: 460343 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.2939. Min Act: -0.1700
Data Index: 2691384 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.2939. Min Act: -0.1700
Data Index: 7039774 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7001. Min Range: -6.7001
Max Act: 6.2939. Min Act: -0.1700
Data Index: 4991774 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19