Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 450 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.7147. Min Act: -0.1700
Data Index: 6505067 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.7147. Min Act: -0.1700
Data Index: 7732717 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.7147. Min Act: -0.1700
Data Index: 2608134 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6834. Min Act: -0.1700
Data Index: 5198494 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6834. Min Act: -0.1700
Data Index: 4841588 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6834. Min Act: -0.1700
Data Index: 454814 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6522. Min Act: -0.1700
Data Index: 2935896 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6834. Min Act: -0.1699
Data Index: 6867532 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6522. Min Act: -0.1700
Data Index: 6467405 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6522. Min Act: -0.1700
Data Index: 1227105 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6522. Min Act: -0.1700
Data Index: 3370161 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6522. Min Act: -0.1700
Data Index: 2008215 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6209. Min Act: -0.1700
Data Index: 4351583 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6209. Min Act: -0.1700
Data Index: 3745338 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.5897. Min Act: -0.1700
Data Index: 7011650 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6209. Min Act: -0.1700
Data Index: 563450 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6209. Min Act: -0.1700
Data Index: 1103888 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6209. Min Act: -0.1700
Data Index: 1347356 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6209. Min Act: -0.1700
Data Index: 859457 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7147. Min Range: -4.7147
Max Act: 4.6209. Min Act: -0.1700
Data Index: 5339157 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19