Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5676 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4133. Min Range: -8.4133
Max Act: 8.4133. Min Act: -0.1700
Data Index: 3966888 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4133. Min Range: -8.4133
Max Act: 8.1008. Min Act: -0.1700
Data Index: 5926254 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4133. Min Range: -8.4133
Max Act: 8.0695. Min Act: -0.1700
Data Index: 8684871 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.9758. Min Act: -0.1700
Data Index: 2776770 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.9445. Min Act: -0.1700
Data Index: 100028 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4133. Min Range: -8.4133
Max Act: 8.0070. Min Act: -0.1700
Data Index: 7682277 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.8820. Min Act: -0.1700
Data Index: 4782236 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.8820. Min Act: -0.1700
Data Index: 1641628 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.8508. Min Act: -0.1700
Data Index: 3680879 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.8195. Min Act: -0.1700
Data Index: 4155876 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.7883. Min Act: -0.1700
Data Index: 2160490 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.7883. Min Act: -0.1700
Data Index: 7831557 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.7258. Min Act: -0.1700
Data Index: 2794468 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.7258. Min Act: -0.1700
Data Index: 7479099 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.6633. Min Act: -0.1700
Data Index: 6642687 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.6320. Min Act: -0.1700
Data Index: 40829 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.6008. Min Act: -0.1700
Data Index: 100029 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.5695. Min Act: -0.1700
Data Index: 7893000 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.5383. Min Act: -0.1697
Data Index: 1395145 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4133. Min Range: -8.4133
Max Act: 7.5383. Min Act: -0.1700
Data Index: 707534 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19