Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2476 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.7165. Min Act: -0.1700
Data Index: 192253 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.6853. Min Act: -0.1700
Data Index: 8231089 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.5290. Min Act: -0.1700
Data Index: 1041970 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.4665. Min Act: -0.1700
Data Index: 717253 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.3415. Min Act: -0.1700
Data Index: 6397795 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.2790. Min Act: -0.1700
Data Index: 258343 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.3103. Min Act: -0.1700
Data Index: 2790143 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.2478. Min Act: -0.1700
Data Index: 1067689 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.2165. Min Act: -0.1700
Data Index: 3949632 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.2165. Min Act: -0.1700
Data Index: 7978437 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.2165. Min Act: -0.1700
Data Index: 1794902 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.1228. Min Act: -0.1700
Data Index: 6878353 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.1228. Min Act: -0.1700
Data Index: 4811686 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.1228. Min Act: -0.1700
Data Index: 1560875 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.1540. Min Act: -0.1700
Data Index: 5856032 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.0915. Min Act: -0.1700
Data Index: 3550747 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.0915. Min Act: -0.1700
Data Index: 7325005 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.0915. Min Act: -0.1700
Data Index: 5294817 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.1228. Min Act: -0.1700
Data Index: 4147953 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7165. Min Range: -7.7165
Max Act: 7.0290. Min Act: -0.1700
Data Index: 1181025 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19