Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4624 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.4369. Min Act: -0.1700
Data Index: 7570008 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.3744. Min Act: -0.1700
Data Index: 5477609 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.3744. Min Act: -0.1700
Data Index: 1730613 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.3119. Min Act: -0.1700
Data Index: 1882652 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.3119. Min Act: -0.1700
Data Index: 2396610 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.2494. Min Act: -0.1700
Data Index: 2832850 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.2494. Min Act: -0.1700
Data Index: 1115894 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.2494. Min Act: -0.1700
Data Index: 4871957 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.2181. Min Act: -0.1700
Data Index: 7468972 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.2494. Min Act: -0.1700
Data Index: 3189041 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.2181. Min Act: -0.1700
Data Index: 6619090 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.1869. Min Act: -0.1700
Data Index: 3525205 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.1869. Min Act: -0.1700
Data Index: 5174367 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.1869. Min Act: -0.1700
Data Index: 8786030 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.1869. Min Act: -0.1700
Data Index: 7339380 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.1556. Min Act: -0.1700
Data Index: 6229549 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.1556. Min Act: -0.1700
Data Index: 7981184 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.1556. Min Act: -0.1700
Data Index: 4556567 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.1556. Min Act: -0.1700
Data Index: 6462495 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4369. Min Range: -4.4369
Max Act: 4.1556. Min Act: -0.1700
Data Index: 2641068 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19