Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3163 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3681. Min Range: -6.3681
Max Act: 6.3681. Min Act: -0.1700
Data Index: 7449851 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3681. Min Range: -6.3681
Max Act: 6.0869. Min Act: -0.1700
Data Index: 8655579 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3681. Min Range: -6.3681
Max Act: 6.1181. Min Act: -0.1700
Data Index: 4350505 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3681. Min Range: -6.3681
Max Act: 6.0556. Min Act: -0.1700
Data Index: 8218275 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3681. Min Range: -6.3681
Max Act: 6.0556. Min Act: -0.1700
Data Index: 5059797 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3681. Min Range: -6.3681
Max Act: 5.9931. Min Act: -0.1700
Data Index: 8457752 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3681. Min Range: -6.3681
Max Act: 5.9619. Min Act: -0.1700
Data Index: 6039205 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3681. Min Range: -6.3681
Max Act: 5.9619. Min Act: -0.1700
Data Index: 1905415 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3681. Min Range: -6.3681
Max Act: 5.9306. Min Act: -0.1700
Data Index: 5602804 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3681. Min Range: -6.3681
Max Act: 5.8681. Min Act: -0.1700
Data Index: 2968226 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3681. Min Range: -6.3681
Max Act: 5.8681. Min Act: -0.1700
Data Index: 1743084 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3681. Min Range: -6.3681
Max Act: 5.8056. Min Act: -0.1700
Data Index: 5248549 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3681. Min Range: -6.3681
Max Act: 5.8056. Min Act: -0.1700
Data Index: 739711 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3681. Min Range: -6.3681
Max Act: 5.8056. Min Act: -0.1700
Data Index: 2184254 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3681. Min Range: -6.3681
Max Act: 5.7431. Min Act: -0.1700
Data Index: 7832538 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3681. Min Range: -6.3681
Max Act: 5.7431. Min Act: -0.1700
Data Index: 7598772 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3681. Min Range: -6.3681
Max Act: 5.7431. Min Act: -0.1700
Data Index: 182208 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3681. Min Range: -6.3681
Max Act: 5.7119. Min Act: -0.1700
Data Index: 8505403 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3681. Min Range: -6.3681
Max Act: 5.6806. Min Act: -0.1700
Data Index: 5973909 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3681. Min Range: -6.3681
Max Act: 5.6806. Min Act: -0.1700
Data Index: 5050020 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19