Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.5958. Min Act: -0.1700
Data Index: 7480905 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.5645. Min Act: -0.1700
Data Index: 4919097 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.5020. Min Act: -0.1700
Data Index: 5822001 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.4708. Min Act: -0.1700
Data Index: 3684922 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.4395. Min Act: -0.1700
Data Index: 8272644 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.4395. Min Act: -0.1700
Data Index: 3741557 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.3458. Min Act: -0.1700
Data Index: 5873819 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.3145. Min Act: -0.1700
Data Index: 6798081 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.3458. Min Act: -0.1700
Data Index: 2180504 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.3458. Min Act: -0.1700
Data Index: 2577849 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.3145. Min Act: -0.1700
Data Index: 7477241 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.2833. Min Act: -0.1700
Data Index: 178841 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.3145. Min Act: -0.1700
Data Index: 178842 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.2833. Min Act: -0.1700
Data Index: 2193608 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.2833. Min Act: -0.1700
Data Index: 4676683 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.2520. Min Act: -0.1700
Data Index: 910775 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.2833. Min Act: -0.1700
Data Index: 3626279 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.2833. Min Act: -0.1700
Data Index: 2727803 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.2833. Min Act: -0.1700
Data Index: 1729447 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.2833. Min Act: -0.1700
Data Index: 7652796 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19