Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.9607. Min Act: -0.1700
Data Index: 7653097 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.8045. Min Act: -0.1700
Data Index: 5722802 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.7420. Min Act: -0.1700
Data Index: 4686393 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.6482. Min Act: -0.1700
Data Index: 5923410 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.6482. Min Act: -0.1700
Data Index: 2279674 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.6795. Min Act: -0.1700
Data Index: 2251478 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.5857. Min Act: -0.1700
Data Index: 7090282 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.4920. Min Act: -0.1700
Data Index: 1027312 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.4920. Min Act: -0.1700
Data Index: 147758 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.4920. Min Act: -0.1700
Data Index: 5788728 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.5232. Min Act: -0.1700
Data Index: 568474 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.3982. Min Act: -0.1700
Data Index: 790366 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.3982. Min Act: -0.1700
Data Index: 2782540 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.3670. Min Act: -0.1700
Data Index: 8775089 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.3357. Min Act: -0.1700
Data Index: 7785872 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.3670. Min Act: -0.1700
Data Index: 2251978 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.3670. Min Act: -0.1700
Data Index: 7962800 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.3357. Min Act: -0.1700
Data Index: 6630648 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.3045. Min Act: -0.1700
Data Index: 6002554 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9607. Min Range: -6.9607
Max Act: 6.3357. Min Act: -0.1700
Data Index: 3294914 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19