Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1404 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.9650. Min Act: -0.1700
Data Index: 8720703 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.9650. Min Act: -0.1700
Data Index: 7838964 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.9025. Min Act: -0.1700
Data Index: 7096310 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.8088. Min Act: -0.1700
Data Index: 7316800 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.7463. Min Act: -0.1700
Data Index: 659318 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.7150. Min Act: -0.1700
Data Index: 5816995 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.7150. Min Act: -0.1700
Data Index: 1285790 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.7150. Min Act: -0.1700
Data Index: 3596649 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.7150. Min Act: -0.1700
Data Index: 4428444 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.6838. Min Act: -0.1700
Data Index: 7246690 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.6838. Min Act: -0.1700
Data Index: 4699262 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.6838. Min Act: -0.1700
Data Index: 4037805 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.6838. Min Act: -0.1700
Data Index: 3973383 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.6525. Min Act: -0.1700
Data Index: 8339705 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.6525. Min Act: -0.1700
Data Index: 1535503 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.6838. Min Act: -0.1700
Data Index: 8195567 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.6525. Min Act: -0.1700
Data Index: 4792976 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.6525. Min Act: -0.1700
Data Index: 6727843 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.6525. Min Act: -0.1700
Data Index: 6194211 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9650. Min Range: -4.9650
Max Act: 4.6525. Min Act: -0.1700
Data Index: 4485837 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19