Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4020 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2151. Min Range: -8.2151
Max Act: 8.2151. Min Act: -0.1700
Data Index: 3564788 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.7776. Min Act: -0.1700
Data Index: 4895344 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.7151. Min Act: -0.1700
Data Index: 326228 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.6213. Min Act: -0.1700
Data Index: 5925839 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.5276. Min Act: -0.1700
Data Index: 2137298 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.4651. Min Act: -0.1700
Data Index: 2579879 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.4026. Min Act: -0.1700
Data Index: 2137292 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.3088. Min Act: -0.1700
Data Index: 1392171 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.3088. Min Act: -0.1700
Data Index: 628769 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.2151. Min Act: -0.1700
Data Index: 1451639 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.1838. Min Act: -0.1700
Data Index: 5039607 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.1838. Min Act: -0.1700
Data Index: 5807973 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.1838. Min Act: -0.1700
Data Index: 5350554 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.1526. Min Act: -0.1700
Data Index: 1680388 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.1526. Min Act: -0.1700
Data Index: 3641804 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.1213. Min Act: -0.1700
Data Index: 5312077 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.1526. Min Act: -0.1700
Data Index: 4417125 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.0901. Min Act: -0.1700
Data Index: 1406473 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.1213. Min Act: -0.1700
Data Index: 4666885 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2151. Min Range: -8.2151
Max Act: 7.1213. Min Act: -0.1700
Data Index: 5833541 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19