Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3707 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1333. Min Range: -3.1333
Max Act: 3.1333. Min Act: -0.1700
Data Index: 7562143 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1333. Min Range: -3.1333
Max Act: 3.0545. Min Act: -0.1700
Data Index: 1046222 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.9439. Min Act: -0.1700
Data Index: 4193341 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.9122. Min Act: -0.1700
Data Index: 1643603 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.9122. Min Act: -0.1700
Data Index: 3361445 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.8963. Min Act: -0.1700
Data Index: 862317 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.8805. Min Act: -0.1700
Data Index: 4078351 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.8805. Min Act: -0.1700
Data Index: 1701937 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.8805. Min Act: -0.1700
Data Index: 4192436 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.8805. Min Act: -0.1700
Data Index: 5970764 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.8646. Min Act: -0.1700
Data Index: 6498364 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.8487. Min Act: -0.1700
Data Index: 6676109 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.8328. Min Act: -0.1700
Data Index: 2624053 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.8328. Min Act: -0.1700
Data Index: 698526 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.8169. Min Act: -0.1700
Data Index: 8415290 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.8169. Min Act: -0.1700
Data Index: 5185501 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.8169. Min Act: -0.1700
Data Index: 8059504 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.8169. Min Act: -0.1700
Data Index: 647817 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.8010. Min Act: -0.1700
Data Index: 7473460 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1333. Min Range: -3.1333
Max Act: 2.7851. Min Act: -0.1700
Data Index: 1841804 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19