Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4270 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4703. Min Range: -12.4703
Max Act: 12.4703. Min Act: -0.1700
Data Index: 4293785 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4703. Min Range: -12.4703
Max Act: 12.2203. Min Act: -0.1700
Data Index: 4606645 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.9703. Min Act: -0.1700
Data Index: 225289 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.9078. Min Act: -0.1700
Data Index: 1367554 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.8453. Min Act: -0.1700
Data Index: 5218598 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.8453. Min Act: -0.1700
Data Index: 7513429 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.8453. Min Act: -0.1700
Data Index: 4552548 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.7828. Min Act: -0.1700
Data Index: 8315666 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.7828. Min Act: -0.1700
Data Index: 6250612 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.7828. Min Act: -0.1700
Data Index: 312246 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.7203. Min Act: -0.1700
Data Index: 1848597 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.7203. Min Act: -0.1700
Data Index: 7767092 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.7203. Min Act: -0.1700
Data Index: 6270041 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.5953. Min Act: -0.1700
Data Index: 7884319 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.5328. Min Act: -0.1700
Data Index: 7666289 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.5328. Min Act: -0.1700
Data Index: 1644539 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.5953. Min Act: -0.1700
Data Index: 8745135 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.5328. Min Act: -0.1700
Data Index: 1526257 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.4703. Min Act: -0.1700
Data Index: 7975090 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4703. Min Range: -12.4703
Max Act: 11.4078. Min Act: -0.1700
Data Index: 5495879 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19