Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 655 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.2285. Min Act: -0.1700
Data Index: 7951416 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.0097. Min Act: -0.1700
Data Index: 3916826 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.9472. Min Act: -0.1700
Data Index: 6318466 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.9472. Min Act: -0.1700
Data Index: 6581978 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.9472. Min Act: -0.1700
Data Index: 8050841 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.9472. Min Act: -0.1700
Data Index: 1799482 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.9160. Min Act: -0.1700
Data Index: 8407637 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.8847. Min Act: -0.1700
Data Index: 217199 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.8847. Min Act: -0.1700
Data Index: 209966 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.8534. Min Act: -0.1700
Data Index: 143132 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.8534. Min Act: -0.1700
Data Index: 2944897 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.8534. Min Act: -0.1700
Data Index: 1255851 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.8221. Min Act: -0.1700
Data Index: 3604628 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.8221. Min Act: -0.1700
Data Index: 6244333 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.8221. Min Act: -0.1700
Data Index: 6172693 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.8221. Min Act: -0.1700
Data Index: 5947185 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.8221. Min Act: -0.1700
Data Index: 5880242 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.8221. Min Act: -0.1700
Data Index: 5525868 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.8221. Min Act: -0.1700
Data Index: 4743468 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2285. Min Range: -4.2285
Max Act: 3.8534. Min Act: -0.1700
Data Index: 623143 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19