Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4724 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.7043. Min Act: -0.1700
Data Index: 6945252 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.7043. Min Act: -0.1700
Data Index: 6275376 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.7043. Min Act: -0.1700
Data Index: 7320730 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.7043. Min Act: -0.1700
Data Index: 1559112 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.7043. Min Act: -0.1700
Data Index: 7930521 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.7043. Min Act: -0.1700
Data Index: 1626792 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.6731. Min Act: -0.1700
Data Index: 8548758 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.6418. Min Act: -0.1700
Data Index: 908344 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.6418. Min Act: -0.1700
Data Index: 4397941 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5793. Min Act: -0.1700
Data Index: 6799914 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5793. Min Act: -0.1700
Data Index: 6894700 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5793. Min Act: -0.1700
Data Index: 3978787 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5481. Min Act: -0.1700
Data Index: 3089089 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5481. Min Act: -0.1700
Data Index: 2070656 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5481. Min Act: -0.1700
Data Index: 6548870 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5793. Min Act: -0.1700
Data Index: 5389179 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 3430918 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5481. Min Act: -0.1700
Data Index: 3008039 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 7142569 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 6271509 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19