Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2737 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.9171. Min Act: -0.1700
Data Index: 8520736 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.9171. Min Act: -0.1700
Data Index: 8038590 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.8858. Min Act: -0.1700
Data Index: 4535466 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.8233. Min Act: -0.1700
Data Index: 7117434 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.8233. Min Act: -0.1700
Data Index: 4634421 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.7921. Min Act: -0.1700
Data Index: 3957923 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.7921. Min Act: -0.1700
Data Index: 8482452 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.7921. Min Act: -0.1700
Data Index: 8413899 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.7921. Min Act: -0.1700
Data Index: 3734802 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.7921. Min Act: -0.1700
Data Index: 4880036 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.7608. Min Act: -0.1700
Data Index: 3616240 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.7608. Min Act: -0.1700
Data Index: 5129730 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.7296. Min Act: -0.1700
Data Index: 37118 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.7608. Min Act: -0.1700
Data Index: 8088269 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.7296. Min Act: -0.1700
Data Index: 5838792 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.7608. Min Act: -0.1700
Data Index: 2047603 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.7296. Min Act: -0.1700
Data Index: 2441247 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.7608. Min Act: -0.1700
Data Index: 37122 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.6983. Min Act: -0.1700
Data Index: 7167028 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9171. Min Range: -4.9171
Max Act: 4.6983. Min Act: -0.1700
Data Index: 838302 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19