Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4074 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.7863. Min Act: -0.1700
Data Index: 7334344 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.6925. Min Act: -0.1700
Data Index: 1852304 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.6925. Min Act: -0.1700
Data Index: 1647718 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.6300. Min Act: -0.1700
Data Index: 6687706 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.5363. Min Act: -0.1700
Data Index: 4298504 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.5363. Min Act: -0.1700
Data Index: 6472402 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.5363. Min Act: -0.1700
Data Index: 7294056 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.5363. Min Act: -0.1700
Data Index: 8148066 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.5050. Min Act: -0.1700
Data Index: 330086 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.4738. Min Act: -0.1700
Data Index: 5260009 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.4425. Min Act: -0.1700
Data Index: 5688135 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.4738. Min Act: -0.1700
Data Index: 2497265 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.5050. Min Act: -0.1700
Data Index: 2754044 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.4738. Min Act: -0.1700
Data Index: 7944356 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.4425. Min Act: -0.1700
Data Index: 7965518 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.4425. Min Act: -0.1700
Data Index: 920499 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.4425. Min Act: -0.1700
Data Index: 5870834 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.4425. Min Act: -0.1700
Data Index: 785896 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.4425. Min Act: -0.1700
Data Index: 6335324 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7863. Min Range: -4.7863
Max Act: 4.4113. Min Act: -0.1700
Data Index: 684473 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19