Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 727 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.6650. Min Act: -0.1700
Data Index: 6826594 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.6963. Min Act: -0.1700
Data Index: 583829 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.5400. Min Act: -0.1700
Data Index: 6518260 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.5400. Min Act: -0.1700
Data Index: 2964398 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.5088. Min Act: -0.1700
Data Index: 8408778 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.5088. Min Act: -0.1700
Data Index: 3066450 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.5088. Min Act: -0.1700
Data Index: 3965514 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.4775. Min Act: -0.1700
Data Index: 3671554 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.4775. Min Act: -0.1700
Data Index: 4133926 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.4775. Min Act: -0.1700
Data Index: 625488 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.4775. Min Act: -0.1700
Data Index: 1490745 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.4463. Min Act: -0.1700
Data Index: 1155394 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.4463. Min Act: -0.1700
Data Index: 113681 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.4463. Min Act: -0.1700
Data Index: 7819254 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.4463. Min Act: -0.1700
Data Index: 5264745 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.4463. Min Act: -0.1700
Data Index: 8577086 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.4150. Min Act: -0.1700
Data Index: 3671556 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.4150. Min Act: -0.1700
Data Index: 1064200 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.3838. Min Act: -0.1700
Data Index: 7253388 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6963. Min Range: -4.6963
Max Act: 4.3838. Min Act: -0.1700
Data Index: 4464831 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19