Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2246 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.3789. Min Act: -0.1700
Data Index: 7781194 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.2539. Min Act: -0.1700
Data Index: 970414 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.2539. Min Act: -0.1700
Data Index: 675322 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.2539. Min Act: -0.1700
Data Index: 4156578 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.2539. Min Act: -0.1700
Data Index: 7896622 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.1914. Min Act: -0.1700
Data Index: 5190781 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.1289. Min Act: -0.1700
Data Index: 4044965 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.1289. Min Act: -0.1700
Data Index: 8121930 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.1289. Min Act: -0.1700
Data Index: 4831771 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.0976. Min Act: -0.1700
Data Index: 1078351 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.0976. Min Act: -0.1700
Data Index: 7542254 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.0664. Min Act: -0.1700
Data Index: 2380042 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.0664. Min Act: -0.1700
Data Index: 4044689 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.0351. Min Act: -0.1700
Data Index: 7627085 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.0039. Min Act: -0.1700
Data Index: 6082405 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3789. Min Range: -6.3789
Max Act: 6.0351. Min Act: -0.1700
Data Index: 2618243 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3789. Min Range: -6.3789
Max Act: 5.9726. Min Act: -0.1700
Data Index: 2231107 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3789. Min Range: -6.3789
Max Act: 5.9726. Min Act: -0.1700
Data Index: 7774735 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3789. Min Range: -6.3789
Max Act: 5.9726. Min Act: -0.1700
Data Index: 6598516 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3789. Min Range: -6.3789
Max Act: 5.9414. Min Act: -0.1700
Data Index: 4802777 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19