Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4170 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.9520. Min Act: -0.1700
Data Index: 5927641 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.9350. Min Act: -0.1700
Data Index: 63676 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.9180. Min Act: -0.1700
Data Index: 6663805 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.8839. Min Act: -0.1700
Data Index: 5760270 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.9009. Min Act: -0.1700
Data Index: 5518745 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.9009. Min Act: -0.1700
Data Index: 1431645 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.9009. Min Act: -0.1700
Data Index: 7270652 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.9009. Min Act: -0.1700
Data Index: 909378 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.8839. Min Act: -0.1700
Data Index: 6424291 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.8839. Min Act: -0.1700
Data Index: 7893156 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.8668. Min Act: -0.1700
Data Index: 6661742 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.8497. Min Act: -0.1700
Data Index: 6227725 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.8668. Min Act: -0.1700
Data Index: 3527772 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.8668. Min Act: -0.1700
Data Index: 5029142 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.8668. Min Act: -0.1700
Data Index: 3876463 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.8497. Min Act: -0.1700
Data Index: 2704687 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.8325. Min Act: -0.1700
Data Index: 3337595 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.8497. Min Act: -0.1700
Data Index: 8017444 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.8497. Min Act: -0.1700
Data Index: 3885935 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9520. Min Range: -1.9520
Max Act: 1.8497. Min Act: -0.1700
Data Index: 498804 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19