Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0211. Min Range: -9.0211
Max Act: 9.0211. Min Act: -0.1700
Data Index: 4497554 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.8961. Min Act: -0.1700
Data Index: 1176878 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.8336. Min Act: -0.1700
Data Index: 8185791 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.8336. Min Act: -0.1700
Data Index: 3864917 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.8336. Min Act: -0.1700
Data Index: 2141196 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.7711. Min Act: -0.1700
Data Index: 5766643 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.7086. Min Act: -0.1700
Data Index: 4600864 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.7086. Min Act: -0.1700
Data Index: 2042753 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.7086. Min Act: -0.1700
Data Index: 453217 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.7086. Min Act: -0.1700
Data Index: 453216 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.7086. Min Act: -0.1700
Data Index: 1246199 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.5836. Min Act: -0.1700
Data Index: 787794 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.6461. Min Act: -0.1700
Data Index: 2807747 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.7086. Min Act: -0.1700
Data Index: 1299979 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.6461. Min Act: -0.1700
Data Index: 3888591 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.6461. Min Act: -0.1700
Data Index: 455825 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.6461. Min Act: -0.1700
Data Index: 8208223 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.6461. Min Act: -0.1700
Data Index: 8021169 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.6461. Min Act: -0.1700
Data Index: 2702706 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0211. Min Range: -9.0211
Max Act: 8.5836. Min Act: -0.1700
Data Index: 6024204 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19