Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4661 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.6968. Min Act: -0.1700
Data Index: 130502 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.7593. Min Act: -0.1700
Data Index: 4443613 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.6968. Min Act: -0.1700
Data Index: 1543696 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.6968. Min Act: -0.1700
Data Index: 1414805 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.6343. Min Act: -0.1700
Data Index: 7662071 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.6343. Min Act: -0.1700
Data Index: 688242 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.6031. Min Act: -0.1700
Data Index: 2835953 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.5718. Min Act: -0.1700
Data Index: 4690160 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.5718. Min Act: -0.1700
Data Index: 75353 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.5406. Min Act: -0.1700
Data Index: 2496429 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.5718. Min Act: -0.1700
Data Index: 2013917 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.5718. Min Act: -0.1700
Data Index: 4690806 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.5093. Min Act: -0.1700
Data Index: 843536 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.5718. Min Act: -0.1700
Data Index: 4963813 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.4781. Min Act: -0.1700
Data Index: 5860437 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.5406. Min Act: -0.1700
Data Index: 2258428 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.5406. Min Act: -0.1700
Data Index: 316429 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.5406. Min Act: -0.1700
Data Index: 7022722 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.4781. Min Act: -0.1700
Data Index: 5268825 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7593. Min Range: -7.7593
Max Act: 7.4781. Min Act: -0.1700
Data Index: 3191834 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19