Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3115 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.5242. Min Act: -0.1700
Data Index: 2881752 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.4930. Min Act: -0.1700
Data Index: 7382894 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.4930. Min Act: -0.1700
Data Index: 3811587 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.4930. Min Act: -0.1700
Data Index: 4624575 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.4617. Min Act: -0.1700
Data Index: 7421547 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.4305. Min Act: -0.1700
Data Index: 8024500 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.4305. Min Act: -0.1700
Data Index: 7766160 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.4617. Min Act: -0.1700
Data Index: 2351810 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.4305. Min Act: -0.1700
Data Index: 1881996 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.4617. Min Act: -0.1700
Data Index: 6643444 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.4305. Min Act: -0.1700
Data Index: 2533421 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.3367. Min Act: -0.1700
Data Index: 8788953 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.3367. Min Act: -0.1700
Data Index: 7075167 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.2430. Min Act: -0.1700
Data Index: 4158181 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.2117. Min Act: -0.1700
Data Index: 6509148 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.1805. Min Act: -0.1700
Data Index: 5020353 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.2117. Min Act: -0.1700
Data Index: 1320711 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.1805. Min Act: -0.1700
Data Index: 7367915 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.1805. Min Act: -0.1700
Data Index: 1262032 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5242. Min Range: -6.5242
Max Act: 6.1805. Min Act: -0.1700
Data Index: 4249829 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19