Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2504 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.9052. Min Act: -0.1700
Data Index: 1230665 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.6864. Min Act: -0.1700
Data Index: 961230 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.6864. Min Act: -0.1700
Data Index: 1230660 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.4677. Min Act: -0.1700
Data Index: 3712424 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.4989. Min Act: -0.1700
Data Index: 1230658 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.4989. Min Act: -0.1700
Data Index: 1230662 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.4989. Min Act: -0.1700
Data Index: 1230664 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.4052. Min Act: -0.1700
Data Index: 1929980 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.3739. Min Act: -0.1700
Data Index: 1720868 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.3427. Min Act: -0.1700
Data Index: 1404781 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.3114. Min Act: -0.1700
Data Index: 2546206 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.2802. Min Act: -0.1700
Data Index: 1230657 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.3114. Min Act: -0.1700
Data Index: 3476005 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.3427. Min Act: -0.1700
Data Index: 1230652 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.2802. Min Act: -0.1700
Data Index: 5522885 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.2177. Min Act: -0.1700
Data Index: 1230653 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.2177. Min Act: -0.1700
Data Index: 4448208 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.1864. Min Act: -0.1700
Data Index: 1230654 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.1864. Min Act: -0.1700
Data Index: 3793579 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9052. Min Range: -5.9052
Max Act: 5.1864. Min Act: -0.1700
Data Index: 2693430 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19