Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1836 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3906. Min Range: -6.3906
Max Act: 6.3906. Min Act: -0.1700
Data Index: 4414804 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3906. Min Range: -6.3906
Max Act: 6.3281. Min Act: -0.1700
Data Index: 949511 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3906. Min Range: -6.3906
Max Act: 6.2343. Min Act: -0.1700
Data Index: 1795630 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3906. Min Range: -6.3906
Max Act: 6.1406. Min Act: -0.1700
Data Index: 1270748 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3906. Min Range: -6.3906
Max Act: 6.1093. Min Act: -0.1700
Data Index: 5601964 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3906. Min Range: -6.3906
Max Act: 6.0781. Min Act: -0.1700
Data Index: 1903982 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3906. Min Range: -6.3906
Max Act: 6.0468. Min Act: -0.1700
Data Index: 8550163 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3906. Min Range: -6.3906
Max Act: 6.1093. Min Act: -0.1700
Data Index: 1715861 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3906. Min Range: -6.3906
Max Act: 6.0468. Min Act: -0.1700
Data Index: 2521580 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3906. Min Range: -6.3906
Max Act: 6.0468. Min Act: -0.1700
Data Index: 6978013 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3906. Min Range: -6.3906
Max Act: 5.9843. Min Act: -0.1700
Data Index: 2977002 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3906. Min Range: -6.3906
Max Act: 5.9531. Min Act: -0.1700
Data Index: 1004885 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3906. Min Range: -6.3906
Max Act: 5.9843. Min Act: -0.1700
Data Index: 3717886 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3906. Min Range: -6.3906
Max Act: 5.9218. Min Act: -0.1700
Data Index: 7063692 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3906. Min Range: -6.3906
Max Act: 5.9218. Min Act: -0.1700
Data Index: 5374813 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3906. Min Range: -6.3906
Max Act: 5.9218. Min Act: -0.1700
Data Index: 2394862 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3906. Min Range: -6.3906
Max Act: 5.9218. Min Act: -0.1700
Data Index: 5304271 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3906. Min Range: -6.3906
Max Act: 5.9218. Min Act: -0.1700
Data Index: 6293698 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3906. Min Range: -6.3906
Max Act: 5.9531. Min Act: -0.1700
Data Index: 2825577 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3906. Min Range: -6.3906
Max Act: 5.8593. Min Act: -0.1700
Data Index: 7121741 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19