Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2735 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.9431. Min Act: -0.1700
Data Index: 7851212 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.9431. Min Act: -0.1700
Data Index: 1604663 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.8806. Min Act: -0.1700
Data Index: 6133853 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.8494. Min Act: -0.1700
Data Index: 3288106 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.8494. Min Act: -0.1700
Data Index: 912072 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.7869. Min Act: -0.1700
Data Index: 134214 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.7869. Min Act: -0.1700
Data Index: 2042154 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.7244. Min Act: -0.1700
Data Index: 1061322 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.6931. Min Act: -0.1700
Data Index: 5306697 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.6619. Min Act: -0.1700
Data Index: 6575878 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.5994. Min Act: -0.1700
Data Index: 3147724 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.5994. Min Act: -0.1700
Data Index: 5277215 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.5369. Min Act: -0.1700
Data Index: 8505689 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.5681. Min Act: -0.1700
Data Index: 3528455 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.5681. Min Act: -0.1700
Data Index: 227559 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.5369. Min Act: -0.1700
Data Index: 7929737 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.5681. Min Act: -0.1700
Data Index: 3103828 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.5369. Min Act: -0.1700
Data Index: 5234286 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.5369. Min Act: -0.1700
Data Index: 2157183 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9431. Min Range: -5.9431
Max Act: 5.5369. Min Act: -0.1700
Data Index: 4472126 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19