Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.5011. Min Act: -0.1700
Data Index: 5180783 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.4699. Min Act: -0.1700
Data Index: 1470102 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.3136. Min Act: -0.1700
Data Index: 1231230 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.2199. Min Act: -0.1700
Data Index: 6264493 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.1886. Min Act: -0.1700
Data Index: 5384502 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.1886. Min Act: -0.1700
Data Index: 3554218 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.1574. Min Act: -0.1700
Data Index: 236348 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.1574. Min Act: -0.1700
Data Index: 7443829 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.1574. Min Act: -0.1700
Data Index: 4742654 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.1574. Min Act: -0.1700
Data Index: 2463954 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.1574. Min Act: -0.1700
Data Index: 8560251 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.1574. Min Act: -0.1700
Data Index: 2129072 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.1574. Min Act: -0.1700
Data Index: 1867858 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.1574. Min Act: -0.1700
Data Index: 3331502 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.1574. Min Act: -0.1700
Data Index: 5510749 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.1574. Min Act: -0.1700
Data Index: 3053106 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.1261. Min Act: -0.1700
Data Index: 6209045 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.1261. Min Act: -0.1700
Data Index: 3604970 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.1261. Min Act: -0.1700
Data Index: 7440914 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5011. Min Range: -5.5011
Max Act: 5.0949. Min Act: -0.1700
Data Index: 8257205 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19