Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4758 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0565. Min Range: -5.0565
Max Act: 5.0565. Min Act: -0.1700
Data Index: 8155761 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.8378. Min Act: -0.1700
Data Index: 5964512 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.7128. Min Act: -0.1700
Data Index: 6938518 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.6815. Min Act: -0.1700
Data Index: 4334377 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.6815. Min Act: -0.1700
Data Index: 1005781 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.6815. Min Act: -0.1700
Data Index: 6696949 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.6503. Min Act: -0.1700
Data Index: 4117348 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.6503. Min Act: -0.1700
Data Index: 3281577 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.6503. Min Act: -0.1700
Data Index: 3202951 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.6190. Min Act: -0.1700
Data Index: 5814980 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.5878. Min Act: -0.1700
Data Index: 3171463 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.5878. Min Act: -0.1700
Data Index: 6582416 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.5878. Min Act: -0.1700
Data Index: 3433872 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.5878. Min Act: -0.1700
Data Index: 8590004 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.5878. Min Act: -0.1700
Data Index: 476930 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.5565. Min Act: -0.1700
Data Index: 5927176 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.5565. Min Act: -0.1700
Data Index: 6710055 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.5565. Min Act: -0.1700
Data Index: 5772257 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.5565. Min Act: -0.1700
Data Index: 6158372 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0565. Min Range: -5.0565
Max Act: 4.5253. Min Act: -0.1700
Data Index: 3075150 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19