Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4188 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.7072. Min Act: -0.1700
Data Index: 383908 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.5197. Min Act: -0.1700
Data Index: 4737052 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.3322. Min Act: -0.1700
Data Index: 2842961 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.3634. Min Act: -0.1700
Data Index: 5795623 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.3634. Min Act: -0.1700
Data Index: 2347755 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.3009. Min Act: -0.1700
Data Index: 1478262 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.3322. Min Act: -0.1700
Data Index: 7794799 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.2384. Min Act: -0.1700
Data Index: 1385225 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.2697. Min Act: -0.1700
Data Index: 3246791 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.3009. Min Act: -0.1700
Data Index: 1463268 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.2384. Min Act: -0.1700
Data Index: 5414148 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.2072. Min Act: -0.1700
Data Index: 4144773 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.2384. Min Act: -0.1700
Data Index: 461060 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.1759. Min Act: -0.1700
Data Index: 1078042 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.1759. Min Act: -0.1700
Data Index: 3537137 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.1134. Min Act: -0.1700
Data Index: 706438 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.1134. Min Act: -0.1700
Data Index: 2866279 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.0822. Min Act: -0.1700
Data Index: 1751692 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.0822. Min Act: -0.1700
Data Index: 1450234 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7072. Min Range: -7.7072
Max Act: 7.0822. Min Act: -0.1700
Data Index: 6062363 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19