Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3109 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2817. Min Range: -7.2817
Max Act: 7.2817. Min Act: -0.1700
Data Index: 8613063 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2817. Min Range: -7.2817
Max Act: 7.2505. Min Act: -0.1700
Data Index: 4863713 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2817. Min Range: -7.2817
Max Act: 7.0317. Min Act: -0.1700
Data Index: 3177724 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2817. Min Range: -7.2817
Max Act: 7.0317. Min Act: -0.1700
Data Index: 8627320 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2817. Min Range: -7.2817
Max Act: 7.0317. Min Act: -0.1700
Data Index: 705758 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2817. Min Range: -7.2817
Max Act: 6.9692. Min Act: -0.1700
Data Index: 4513930 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2817. Min Range: -7.2817
Max Act: 6.9380. Min Act: -0.1700
Data Index: 8382739 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2817. Min Range: -7.2817
Max Act: 6.9380. Min Act: -0.1700
Data Index: 3379865 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2817. Min Range: -7.2817
Max Act: 6.9692. Min Act: -0.1700
Data Index: 7529489 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2817. Min Range: -7.2817
Max Act: 6.9380. Min Act: -0.1700
Data Index: 6207416 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2817. Min Range: -7.2817
Max Act: 6.9692. Min Act: -0.1700
Data Index: 2055489 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2817. Min Range: -7.2817
Max Act: 6.8755. Min Act: -0.1700
Data Index: 5959207 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2817. Min Range: -7.2817
Max Act: 6.9067. Min Act: -0.1700
Data Index: 6468367 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2817. Min Range: -7.2817
Max Act: 6.8755. Min Act: -0.1700
Data Index: 462431 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2817. Min Range: -7.2817
Max Act: 6.8442. Min Act: -0.1700
Data Index: 2158505 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2817. Min Range: -7.2817
Max Act: 6.8442. Min Act: -0.1700
Data Index: 5590266 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2817. Min Range: -7.2817
Max Act: 6.8130. Min Act: -0.1700
Data Index: 8166028 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2817. Min Range: -7.2817
Max Act: 6.8130. Min Act: -0.1700
Data Index: 7124499 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2817. Min Range: -7.2817
Max Act: 6.8130. Min Act: -0.1700
Data Index: 4147195 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2817. Min Range: -7.2817
Max Act: 6.7817. Min Act: -0.1700
Data Index: 3892078 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19