Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2403 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1899. Min Range: -5.1899
Max Act: 5.1899. Min Act: -0.1700
Data Index: 1118815 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1899. Min Range: -5.1899
Max Act: 5.0649. Min Act: -0.1700
Data Index: 7752889 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1899. Min Range: -5.1899
Max Act: 5.0024. Min Act: -0.1700
Data Index: 7161525 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1899. Min Range: -5.1899
Max Act: 5.0024. Min Act: -0.1700
Data Index: 8002250 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.9711. Min Act: -0.1700
Data Index: 3950572 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.9711. Min Act: -0.1700
Data Index: 4009154 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.9399. Min Act: -0.1700
Data Index: 665434 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.9399. Min Act: -0.1700
Data Index: 8008369 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.9399. Min Act: -0.1700
Data Index: 3001784 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.9399. Min Act: -0.1700
Data Index: 2259682 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.9399. Min Act: -0.1700
Data Index: 705548 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.9086. Min Act: -0.1700
Data Index: 6730639 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.9086. Min Act: -0.1700
Data Index: 4288711 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.9086. Min Act: -0.1700
Data Index: 3517221 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.9086. Min Act: -0.1700
Data Index: 6389774 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.9086. Min Act: -0.1700
Data Index: 942781 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.8774. Min Act: -0.1700
Data Index: 6998880 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.8774. Min Act: -0.1700
Data Index: 4306005 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.8774. Min Act: -0.1700
Data Index: 160207 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1899. Min Range: -5.1899
Max Act: 4.8774. Min Act: -0.1700
Data Index: 7023890 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19