Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3579 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.8165. Min Act: -0.1700
Data Index: 3409184 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.5040. Min Act: -0.1700
Data Index: 5724585 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.3790. Min Act: -0.1700
Data Index: 2778678 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.3790. Min Act: -0.1700
Data Index: 1299577 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.3477. Min Act: -0.1700
Data Index: 8206351 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.2539. Min Act: -0.1700
Data Index: 1152377 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.2539. Min Act: -0.1700
Data Index: 2055702 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.2539. Min Act: -0.1700
Data Index: 1886544 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.2227. Min Act: -0.1700
Data Index: 5250104 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.1914. Min Act: -0.1700
Data Index: 545182 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.2539. Min Act: -0.1700
Data Index: 121785 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.2227. Min Act: -0.1700
Data Index: 2353950 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.1914. Min Act: -0.1700
Data Index: 6236373 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.1914. Min Act: -0.1700
Data Index: 5926422 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.1602. Min Act: -0.1700
Data Index: 2675563 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.1914. Min Act: -0.1700
Data Index: 1535739 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.1914. Min Act: -0.1700
Data Index: 4994357 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.1914. Min Act: -0.1700
Data Index: 1014949 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.1914. Min Act: -0.1700
Data Index: 2057938 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8165. Min Range: -4.8165
Max Act: 4.1914. Min Act: -0.1700
Data Index: 2810232 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19