Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5768 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5847. Min Range: -7.5847
Max Act: 7.5847. Min Act: -0.1700
Data Index: 4154736 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5847. Min Range: -7.5847
Max Act: 7.0847. Min Act: -0.1700
Data Index: 4154737 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.7722. Min Act: -0.1700
Data Index: 2685497 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.7722. Min Act: -0.1700
Data Index: 1504215 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.6472. Min Act: -0.1700
Data Index: 4841871 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.7097. Min Act: -0.1700
Data Index: 7293124 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.6784. Min Act: -0.1700
Data Index: 1438615 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.6472. Min Act: -0.1700
Data Index: 543149 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.6472. Min Act: -0.1700
Data Index: 8789528 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.5847. Min Act: -0.1700
Data Index: 4475902 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.5534. Min Act: -0.1700
Data Index: 5005894 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.5534. Min Act: -0.1700
Data Index: 1894340 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.5847. Min Act: -0.1700
Data Index: 7035117 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.5222. Min Act: -0.1700
Data Index: 3648852 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.4597. Min Act: -0.1700
Data Index: 4798456 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.4909. Min Act: -0.1700
Data Index: 5643704 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.4597. Min Act: -0.1700
Data Index: 3838864 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.4284. Min Act: -0.1700
Data Index: 2866056 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.4284. Min Act: -0.1700
Data Index: 6180949 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5847. Min Range: -7.5847
Max Act: 6.4284. Min Act: -0.1700
Data Index: 1045212 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19