Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3216 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2805. Min Range: -7.2805
Max Act: 7.2805. Min Act: -0.1700
Data Index: 2545968 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.8118. Min Act: -0.1700
Data Index: 8638648 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.7805. Min Act: -0.1700
Data Index: 8363820 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.7180. Min Act: -0.1700
Data Index: 2372126 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.7180. Min Act: -0.1700
Data Index: 1903817 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.7180. Min Act: -0.1700
Data Index: 4029259 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.6555. Min Act: -0.1700
Data Index: 3164303 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.5618. Min Act: -0.1700
Data Index: 6994657 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.4993. Min Act: -0.1700
Data Index: 6390672 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.5305. Min Act: -0.1700
Data Index: 7214908 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.4368. Min Act: -0.1700
Data Index: 4229723 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.4680. Min Act: -0.1700
Data Index: 634655 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.4680. Min Act: -0.1700
Data Index: 1307303 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.4680. Min Act: -0.1700
Data Index: 776618 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.4680. Min Act: -0.1700
Data Index: 1222048 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.4680. Min Act: -0.1700
Data Index: 148902 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.4368. Min Act: -0.1700
Data Index: 1731398 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.4368. Min Act: -0.1700
Data Index: 8004009 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.4368. Min Act: -0.1700
Data Index: 2663382 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2805. Min Range: -7.2805
Max Act: 6.3743. Min Act: -0.1700
Data Index: 6612709 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19