Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4965 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.9754. Min Act: -0.1700
Data Index: 4409434 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.9754. Min Act: -0.1700
Data Index: 7603131 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.9441. Min Act: -0.1700
Data Index: 6162955 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.9129. Min Act: -0.1700
Data Index: 6889541 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.9129. Min Act: -0.1700
Data Index: 4638733 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.9129. Min Act: -0.1700
Data Index: 3730416 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.8816. Min Act: -0.1700
Data Index: 1114645 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.8504. Min Act: -0.1700
Data Index: 2912507 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.8816. Min Act: -0.1700
Data Index: 4294798 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.8191. Min Act: -0.1700
Data Index: 389349 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.8504. Min Act: -0.1700
Data Index: 1225007 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.8504. Min Act: -0.1700
Data Index: 3604252 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.8504. Min Act: -0.1700
Data Index: 5657601 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.8191. Min Act: -0.1700
Data Index: 7706624 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.8191. Min Act: -0.1700
Data Index: 5394980 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.8504. Min Act: -0.1700
Data Index: 4984845 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.8191. Min Act: -0.1700
Data Index: 1380874 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.7566. Min Act: -0.1700
Data Index: 1001119 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.7879. Min Act: -0.1700
Data Index: 5264681 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9754. Min Range: -4.9754
Max Act: 4.7879. Min Act: -0.1700
Data Index: 5072825 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19