Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 909 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.6238. Min Act: -0.1700
Data Index: 309004 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.5611. Min Act: -0.1700
Data Index: 312650 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.4358. Min Act: -0.1700
Data Index: 1561765 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.4358. Min Act: -0.1700
Data Index: 4973202 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.4202. Min Act: -0.1700
Data Index: 4606857 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.4045. Min Act: -0.1700
Data Index: 2503671 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.3888. Min Act: -0.1700
Data Index: 1561760 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.3731. Min Act: -0.1700
Data Index: 2142313 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.3731. Min Act: -0.1700
Data Index: 706069 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.3731. Min Act: -0.1700
Data Index: 8829898 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.3574. Min Act: -0.1700
Data Index: 2938652 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.3574. Min Act: -0.1700
Data Index: 706082 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.3418. Min Act: -0.1700
Data Index: 1561766 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.3418. Min Act: -0.1700
Data Index: 598248 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.3574. Min Act: -0.1700
Data Index: 1561772 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.3418. Min Act: -0.1700
Data Index: 2417250 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.3261. Min Act: -0.1700
Data Index: 1561753 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.3261. Min Act: -0.1700
Data Index: 1645635 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.3261. Min Act: -0.1700
Data Index: 7838926 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6238. Min Range: -3.6238
Max Act: 3.3261. Min Act: -0.1700
Data Index: 2142343 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19