Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1981 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2448. Min Range: -6.2448
Max Act: 6.2448. Min Act: -0.1700
Data Index: 4483971 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.9010. Min Act: -0.1700
Data Index: 713629 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.8698. Min Act: -0.1700
Data Index: 459406 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.8698. Min Act: -0.1700
Data Index: 161175 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.8698. Min Act: -0.1700
Data Index: 5572533 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.8073. Min Act: -0.1700
Data Index: 1876281 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.7448. Min Act: -0.1700
Data Index: 4418206 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.7448. Min Act: -0.1700
Data Index: 1525685 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.7135. Min Act: -0.1700
Data Index: 2671660 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.7135. Min Act: -0.1700
Data Index: 5978681 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.6510. Min Act: -0.1700
Data Index: 2718065 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.6510. Min Act: -0.1695
Data Index: 2178876 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.6823. Min Act: -0.1700
Data Index: 3792947 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.6823. Min Act: -0.1700
Data Index: 7328574 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.6510. Min Act: -0.1700
Data Index: 4977658 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.6198. Min Act: -0.1700
Data Index: 5037540 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.5885. Min Act: -0.1700
Data Index: 4049670 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.6510. Min Act: -0.1700
Data Index: 195484 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.6510. Min Act: -0.1700
Data Index: 3869087 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2448. Min Range: -6.2448
Max Act: 5.6198. Min Act: -0.1700
Data Index: 6793953 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19