Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3779 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.7011. Min Act: -0.1700
Data Index: 6567994 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.6855. Min Act: -0.1700
Data Index: 2484899 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.6386. Min Act: -0.1700
Data Index: 4440087 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.6386. Min Act: -0.1700
Data Index: 8469278 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.6229. Min Act: -0.1700
Data Index: 6324079 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.6229. Min Act: -0.1700
Data Index: 5203253 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.6073. Min Act: -0.1700
Data Index: 1367554 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.5916. Min Act: -0.1700
Data Index: 5001368 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.5916. Min Act: -0.1700
Data Index: 1475795 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.5760. Min Act: -0.1700
Data Index: 4655445 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.5760. Min Act: -0.1700
Data Index: 120532 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.5760. Min Act: -0.1700
Data Index: 756978 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.5603. Min Act: -0.1700
Data Index: 2493518 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.5603. Min Act: -0.1700
Data Index: 2145701 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.5603. Min Act: -0.1700
Data Index: 5213271 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.5446. Min Act: -0.1700
Data Index: 3984200 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.5446. Min Act: -0.1700
Data Index: 1755554 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.5446. Min Act: -0.1700
Data Index: 8424970 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.5446. Min Act: -0.1700
Data Index: 1239798 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7011. Min Range: -3.7011
Max Act: 3.5446. Min Act: -0.1700
Data Index: 4657494 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19