Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3748 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1905. Min Range: -5.1905
Max Act: 5.1905. Min Act: -0.1700
Data Index: 5846783 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1905. Min Range: -5.1905
Max Act: 5.1280. Min Act: -0.1700
Data Index: 4139926 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.9093. Min Act: -0.1700
Data Index: 8593039 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.9093. Min Act: -0.1700
Data Index: 7312682 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.8780. Min Act: -0.1700
Data Index: 5736850 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.8780. Min Act: -0.1700
Data Index: 3429940 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.8468. Min Act: -0.1700
Data Index: 8830085 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.8468. Min Act: -0.1700
Data Index: 1216889 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.8155. Min Act: -0.1700
Data Index: 6809633 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.8155. Min Act: -0.1700
Data Index: 6400919 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.7530. Min Act: -0.1700
Data Index: 7405735 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.7843. Min Act: -0.1700
Data Index: 3583273 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.7530. Min Act: -0.1700
Data Index: 4139928 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.7843. Min Act: -0.1700
Data Index: 236268 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.7530. Min Act: -0.1700
Data Index: 8657458 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.7218. Min Act: -0.1700
Data Index: 1881639 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.7218. Min Act: -0.1700
Data Index: 3577900 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.7218. Min Act: -0.1700
Data Index: 4797102 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.6905. Min Act: -0.1700
Data Index: 5866127 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1905. Min Range: -5.1905
Max Act: 4.6905. Min Act: -0.1700
Data Index: 7826783 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19