Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 680 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.5355. Min Act: -0.1700
Data Index: 7851984 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.5043. Min Act: -0.1700
Data Index: 7851995 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.4418. Min Act: -0.1700
Data Index: 2498313 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.3480. Min Act: -0.1700
Data Index: 3910922 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.3480. Min Act: -0.1700
Data Index: 7063769 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.2855. Min Act: -0.1700
Data Index: 2400166 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.2543. Min Act: -0.1700
Data Index: 2916867 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.2543. Min Act: -0.1700
Data Index: 7650161 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.2543. Min Act: -0.1700
Data Index: 4888269 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.1918. Min Act: -0.1700
Data Index: 1130101 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.1605. Min Act: -0.1700
Data Index: 1526948 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.1605. Min Act: -0.1700
Data Index: 5325661 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.1605. Min Act: -0.1700
Data Index: 1972951 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.1293. Min Act: -0.1700
Data Index: 1620271 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.0980. Min Act: -0.1700
Data Index: 7103199 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.1293. Min Act: -0.1700
Data Index: 2509269 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.0980. Min Act: -0.1700
Data Index: 1126135 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.0668. Min Act: -0.1700
Data Index: 8198429 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.0668. Min Act: -0.1700
Data Index: 118750 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5355. Min Range: -6.5355
Max Act: 6.0355. Min Act: -0.1700
Data Index: 4858002 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19