Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1574 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.1342. Min Act: -0.1700
Data Index: 3473702 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.1175. Min Act: -0.1700
Data Index: 3339495 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.1175. Min Act: -0.1700
Data Index: 4784882 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.1175. Min Act: -0.1700
Data Index: 3809134 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.1008. Min Act: -0.1700
Data Index: 8330995 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.0840. Min Act: -0.1700
Data Index: 7230289 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.0840. Min Act: -0.1700
Data Index: 5167037 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.0840. Min Act: -0.1700
Data Index: 2584911 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.0504. Min Act: -0.1700
Data Index: 5120123 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.0840. Min Act: -0.1700
Data Index: 3141621 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.0840. Min Act: -0.1700
Data Index: 4738998 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.0672. Min Act: -0.1700
Data Index: 4672338 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.0504. Min Act: -0.1700
Data Index: 8828099 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.0672. Min Act: -0.1700
Data Index: 3897047 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.0504. Min Act: -0.1700
Data Index: 4356622 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.0336. Min Act: -0.1700
Data Index: 3512692 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.0336. Min Act: -0.1700
Data Index: 2470209 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.0504. Min Act: -0.1700
Data Index: 4338905 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.0167. Min Act: -0.1700
Data Index: 6289251 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1342. Min Range: -2.1342
Max Act: 2.0167. Min Act: -0.1700
Data Index: 6380703 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19