Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 732 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2593. Min Range: -7.2593
Max Act: 7.2593. Min Act: -0.1700
Data Index: 1777386 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2593. Min Range: -7.2593
Max Act: 7.1031. Min Act: -0.1700
Data Index: 989847 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2593. Min Range: -7.2593
Max Act: 7.1031. Min Act: -0.1700
Data Index: 5421362 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2593. Min Range: -7.2593
Max Act: 7.1031. Min Act: -0.1700
Data Index: 1059337 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2593. Min Range: -7.2593
Max Act: 7.0093. Min Act: -0.1700
Data Index: 3199162 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.9781. Min Act: -0.1700
Data Index: 7845582 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.9468. Min Act: -0.1700
Data Index: 549195 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.8843. Min Act: -0.1700
Data Index: 1267728 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.8531. Min Act: -0.1700
Data Index: 8569477 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.8531. Min Act: -0.1700
Data Index: 7460393 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.8531. Min Act: -0.1700
Data Index: 6241444 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.8218. Min Act: -0.1700
Data Index: 2713109 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.8218. Min Act: -0.1700
Data Index: 711404 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.8218. Min Act: -0.1700
Data Index: 4049631 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.7593. Min Act: -0.1700
Data Index: 2894671 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.7593. Min Act: -0.1700
Data Index: 6273482 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.7593. Min Act: -0.1700
Data Index: 1661696 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.7593. Min Act: -0.1700
Data Index: 4467889 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.7593. Min Act: -0.1700
Data Index: 1153144 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2593. Min Range: -7.2593
Max Act: 6.7593. Min Act: -0.1700
Data Index: 1764495 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19