Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3838 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1454. Min Range: -3.1454
Max Act: 3.1296. Min Act: -0.1700
Data Index: 815177 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1454. Min Range: -3.1454
Max Act: 3.1454. Min Act: -0.1700
Data Index: 2257709 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1454. Min Range: -3.1454
Max Act: 3.0823. Min Act: -0.1700
Data Index: 3321277 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9876. Min Act: -0.1700
Data Index: 8422040 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1454. Min Range: -3.1454
Max Act: 3.0034. Min Act: -0.1700
Data Index: 5151905 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9876. Min Act: -0.1700
Data Index: 2777350 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9560. Min Act: -0.1700
Data Index: 8495650 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9401. Min Act: -0.1700
Data Index: 1010999 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9401. Min Act: -0.1700
Data Index: 6581789 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9243. Min Act: -0.1700
Data Index: 6895649 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9243. Min Act: -0.1700
Data Index: 1444843 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.8926. Min Act: -0.1700
Data Index: 4796169 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.8926. Min Act: -0.1700
Data Index: 8222389 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9084. Min Act: -0.1700
Data Index: 1224932 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9243. Min Act: -0.1700
Data Index: 3911639 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9243. Min Act: -0.1700
Data Index: 1652320 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9084. Min Act: -0.1700
Data Index: 933442 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.8767. Min Act: -0.1700
Data Index: 5490217 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.8926. Min Act: -0.1700
Data Index: 1047433 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1454. Min Range: -3.1454
Max Act: 2.9084. Min Act: -0.1700
Data Index: 3946503 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19