Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.9878. Min Act: -0.1700
Data Index: 1350862 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.8628. Min Act: -0.1700
Data Index: 7727723 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.8628. Min Act: -0.1700
Data Index: 6217931 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.7378. Min Act: -0.1700
Data Index: 763667 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.7378. Min Act: -0.1700
Data Index: 2358668 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.7065. Min Act: -0.1700
Data Index: 879174 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.6440. Min Act: -0.1700
Data Index: 3880268 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.6440. Min Act: -0.1700
Data Index: 7395787 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.6440. Min Act: -0.1700
Data Index: 4738851 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.6440. Min Act: -0.1700
Data Index: 119428 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.6128. Min Act: -0.1700
Data Index: 7205294 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.5815. Min Act: -0.1700
Data Index: 1213998 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.6128. Min Act: -0.1700
Data Index: 3140038 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.6128. Min Act: -0.1700
Data Index: 7098843 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.6128. Min Act: -0.1700
Data Index: 597488 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.5815. Min Act: -0.1700
Data Index: 3411939 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.5503. Min Act: -0.1700
Data Index: 3740581 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.5503. Min Act: -0.1700
Data Index: 1384292 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.5503. Min Act: -0.1700
Data Index: 3914129 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9878. Min Range: -4.9878
Max Act: 4.5190. Min Act: -0.1700
Data Index: 1325028 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19