Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2342 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0737. Min Range: -7.0737
Max Act: 7.0737. Min Act: -0.1700
Data Index: 5857258 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0737. Min Range: -7.0737
Max Act: 7.0425. Min Act: -0.1700
Data Index: 3432561 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.8862. Min Act: -0.1700
Data Index: 5076852 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.8237. Min Act: -0.1700
Data Index: 4917551 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.6987. Min Act: -0.1700
Data Index: 5502033 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.6987. Min Act: -0.1700
Data Index: 7102383 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.6675. Min Act: -0.1700
Data Index: 2834389 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.6362. Min Act: -0.1700
Data Index: 5131123 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.6362. Min Act: -0.1700
Data Index: 2151491 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.6050. Min Act: -0.1700
Data Index: 3656324 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.5425. Min Act: -0.1700
Data Index: 8510858 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.5737. Min Act: -0.1700
Data Index: 964933 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.5425. Min Act: -0.1700
Data Index: 2010690 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.5112. Min Act: -0.1700
Data Index: 6022070 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.5112. Min Act: -0.1700
Data Index: 5807519 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.5112. Min Act: -0.1700
Data Index: 6508873 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.5112. Min Act: -0.1700
Data Index: 3113418 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.4800. Min Act: -0.1700
Data Index: 8699821 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.4800. Min Act: -0.1700
Data Index: 2770130 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0737. Min Range: -7.0737
Max Act: 6.4487. Min Act: -0.1700
Data Index: 6627481 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19