Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2866 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7909. Min Range: -6.7909
Max Act: 6.7909. Min Act: -0.1700
Data Index: 4103660 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7909. Min Range: -6.7909
Max Act: 6.3846. Min Act: -0.1700
Data Index: 6869636 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7909. Min Range: -6.7909
Max Act: 6.2284. Min Act: -0.1700
Data Index: 2043961 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7909. Min Range: -6.7909
Max Act: 6.2596. Min Act: -0.1700
Data Index: 3333193 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7909. Min Range: -6.7909
Max Act: 6.1346. Min Act: -0.1700
Data Index: 924772 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7909. Min Range: -6.7909
Max Act: 6.1034. Min Act: -0.1700
Data Index: 6033277 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7909. Min Range: -6.7909
Max Act: 6.0409. Min Act: -0.1700
Data Index: 6139903 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7909. Min Range: -6.7909
Max Act: 5.9784. Min Act: -0.1700
Data Index: 7698275 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7909. Min Range: -6.7909
Max Act: 6.0409. Min Act: -0.1700
Data Index: 5496771 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7909. Min Range: -6.7909
Max Act: 5.9784. Min Act: -0.1700
Data Index: 8029153 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7909. Min Range: -6.7909
Max Act: 5.9471. Min Act: -0.1700
Data Index: 6725914 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7909. Min Range: -6.7909
Max Act: 5.9784. Min Act: -0.1700
Data Index: 1104639 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7909. Min Range: -6.7909
Max Act: 5.9471. Min Act: -0.1700
Data Index: 5765827 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7909. Min Range: -6.7909
Max Act: 5.9471. Min Act: -0.1700
Data Index: 6312697 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7909. Min Range: -6.7909
Max Act: 5.9159. Min Act: -0.1700
Data Index: 5903520 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7909. Min Range: -6.7909
Max Act: 5.9471. Min Act: -0.1700
Data Index: 3395513 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7909. Min Range: -6.7909
Max Act: 5.9159. Min Act: -0.1700
Data Index: 7610171 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7909. Min Range: -6.7909
Max Act: 5.9159. Min Act: -0.1700
Data Index: 5665960 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7909. Min Range: -6.7909
Max Act: 5.8846. Min Act: -0.1700
Data Index: 104949 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7909. Min Range: -6.7909
Max Act: 5.8846. Min Act: -0.1700
Data Index: 5210287 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19