Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2728 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.9607. Min Act: -0.1700
Data Index: 4417440 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.8357. Min Act: -0.1700
Data Index: 3467928 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.8982. Min Act: -0.1700
Data Index: 7553199 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.7732. Min Act: -0.1700
Data Index: 313231 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.7107. Min Act: -0.1700
Data Index: 1286334 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.7107. Min Act: -0.1700
Data Index: 4364252 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.7107. Min Act: -0.1700
Data Index: 7870640 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.7732. Min Act: -0.1700
Data Index: 7949032 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.7107. Min Act: -0.1700
Data Index: 4468655 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.6482. Min Act: -0.1700
Data Index: 977436 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.7107. Min Act: -0.1700
Data Index: 1303456 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.7107. Min Act: -0.1700
Data Index: 1952078 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.7107. Min Act: -0.1700
Data Index: 4006803 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.7107. Min Act: -0.1700
Data Index: 6509388 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.6482. Min Act: -0.1700
Data Index: 1719878 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.5857. Min Act: -0.1700
Data Index: 1264508 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.5857. Min Act: -0.1700
Data Index: 7939524 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.5232. Min Act: -0.1700
Data Index: 2889820 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.5232. Min Act: -0.1700
Data Index: 1616300 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.5232. Min Act: -0.1700
Data Index: 1143418 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19