Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2584 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4288. Min Range: -6.4288
Max Act: 6.4288. Min Act: -0.1700
Data Index: 6394012 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4288. Min Range: -6.4288
Max Act: 6.2101. Min Act: -0.1700
Data Index: 5251651 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.9913. Min Act: -0.1700
Data Index: 5698304 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.9601. Min Act: -0.1700
Data Index: 5879633 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.9601. Min Act: -0.1700
Data Index: 7153406 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.9601. Min Act: -0.1700
Data Index: 1590179 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.9288. Min Act: -0.1700
Data Index: 8342797 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.8976. Min Act: -0.1700
Data Index: 3255997 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.9288. Min Act: -0.1700
Data Index: 552647 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.8663. Min Act: -0.1700
Data Index: 153476 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.8976. Min Act: -0.1700
Data Index: 8480736 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.8663. Min Act: -0.1700
Data Index: 6867783 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.8038. Min Act: -0.1700
Data Index: 4503265 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.8351. Min Act: -0.1700
Data Index: 5563065 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.8038. Min Act: -0.1700
Data Index: 5237845 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.8038. Min Act: -0.1700
Data Index: 2228767 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.8038. Min Act: -0.1700
Data Index: 3251633 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.7413. Min Act: -0.1700
Data Index: 7375569 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.7726. Min Act: -0.1700
Data Index: 3250048 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4288. Min Range: -6.4288
Max Act: 5.8038. Min Act: -0.1700
Data Index: 8056153 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19