Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4845 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.8250. Min Act: -0.1700
Data Index: 4538711 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.8250. Min Act: -0.1700
Data Index: 5779306 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.8250. Min Act: -0.1700
Data Index: 137953 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.7938. Min Act: -0.1700
Data Index: 1923440 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.7000. Min Act: -0.1700
Data Index: 1472382 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.7000. Min Act: -0.1700
Data Index: 8520027 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.7000. Min Act: -0.1700
Data Index: 2204082 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.6688. Min Act: -0.1700
Data Index: 4682307 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.6688. Min Act: -0.1700
Data Index: 8303641 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.6688. Min Act: -0.1700
Data Index: 4954091 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.6375. Min Act: -0.1700
Data Index: 2639232 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.6375. Min Act: -0.1700
Data Index: 7421119 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.6688. Min Act: -0.1700
Data Index: 3603956 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.6375. Min Act: -0.1700
Data Index: 7554045 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.6375. Min Act: -0.1700
Data Index: 2365059 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.6375. Min Act: -0.1700
Data Index: 4467055 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.6375. Min Act: -0.1700
Data Index: 2178406 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.6375. Min Act: -0.1700
Data Index: 6199851 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.6375. Min Act: -0.1700
Data Index: 3590998 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8250. Min Range: -4.8250
Max Act: 4.6375. Min Act: -0.1700
Data Index: 5873945 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19