Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.7402. Min Act: -0.1700
Data Index: 6586200 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.7714. Min Act: -0.1700
Data Index: 6965305 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.7089. Min Act: -0.1700
Data Index: 503816 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.6464. Min Act: -0.1700
Data Index: 8054343 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.6152. Min Act: -0.1700
Data Index: 81946 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.5839. Min Act: -0.1700
Data Index: 1935758 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.5839. Min Act: -0.1700
Data Index: 6309940 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.5527. Min Act: -0.1700
Data Index: 5118170 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.4902. Min Act: -0.1700
Data Index: 6414343 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.4589. Min Act: -0.1700
Data Index: 1431309 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.4902. Min Act: -0.1700
Data Index: 7220519 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.4902. Min Act: -0.1700
Data Index: 4993308 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.4589. Min Act: -0.1700
Data Index: 3357224 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.4277. Min Act: -0.1700
Data Index: 8307977 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.4277. Min Act: -0.1700
Data Index: 2923727 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.3652. Min Act: -0.1700
Data Index: 2112639 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.3964. Min Act: -0.1700
Data Index: 7803948 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.3339. Min Act: -0.1700
Data Index: 2717605 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.3339. Min Act: -0.1700
Data Index: 1021864 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7714. Min Range: -6.7714
Max Act: 6.3339. Min Act: -0.1700
Data Index: 2385950 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19