Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4317 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2432. Min Range: -4.2432
Max Act: 4.2432. Min Act: -0.1700
Data Index: 6087698 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2432. Min Range: -4.2432
Max Act: 4.2120. Min Act: -0.1700
Data Index: 3064515 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2432. Min Range: -4.2432
Max Act: 4.0869. Min Act: -0.1700
Data Index: 5777070 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2432. Min Range: -4.2432
Max Act: 4.1182. Min Act: -0.1700
Data Index: 180034 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2432. Min Range: -4.2432
Max Act: 4.0869. Min Act: -0.1700
Data Index: 7447558 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2432. Min Range: -4.2432
Max Act: 4.0869. Min Act: -0.1700
Data Index: 4665347 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2432. Min Range: -4.2432
Max Act: 4.0557. Min Act: -0.1700
Data Index: 11219 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2432. Min Range: -4.2432
Max Act: 4.0557. Min Act: -0.1700
Data Index: 2239740 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2432. Min Range: -4.2432
Max Act: 4.0244. Min Act: -0.1700
Data Index: 3332331 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2432. Min Range: -4.2432
Max Act: 4.0244. Min Act: -0.1700
Data Index: 538033 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2432. Min Range: -4.2432
Max Act: 3.9619. Min Act: -0.1700
Data Index: 4055102 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2432. Min Range: -4.2432
Max Act: 3.9619. Min Act: -0.1700
Data Index: 7203662 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2432. Min Range: -4.2432
Max Act: 3.9619. Min Act: -0.1700
Data Index: 5116095 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2432. Min Range: -4.2432
Max Act: 3.9306. Min Act: -0.1700
Data Index: 4445002 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2432. Min Range: -4.2432
Max Act: 3.8994. Min Act: -0.1700
Data Index: 1937153 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2432. Min Range: -4.2432
Max Act: 3.8994. Min Act: -0.1700
Data Index: 2029136 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2432. Min Range: -4.2432
Max Act: 3.8994. Min Act: -0.1700
Data Index: 6133949 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2432. Min Range: -4.2432
Max Act: 3.8994. Min Act: -0.1700
Data Index: 7617475 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2432. Min Range: -4.2432
Max Act: 3.8681. Min Act: -0.1700
Data Index: 2877594 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2432. Min Range: -4.2432
Max Act: 3.8681. Min Act: -0.1700
Data Index: 3701554 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19