Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1417 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.7548. Min Act: -0.1699
Data Index: 4975054 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.6298. Min Act: -0.1700
Data Index: 2807804 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.4110. Min Act: -0.1700
Data Index: 7886291 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.2860. Min Act: -0.1700
Data Index: 721438 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.2548. Min Act: -0.1700
Data Index: 4980528 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.1297. Min Act: -0.1700
Data Index: 7028321 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.1297. Min Act: -0.1700
Data Index: 5014164 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.1297. Min Act: -0.1700
Data Index: 6674776 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.0985. Min Act: -0.1700
Data Index: 533984 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.0985. Min Act: -0.1700
Data Index: 35295 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.0985. Min Act: -0.1700
Data Index: 8692738 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.0985. Min Act: -0.1700
Data Index: 7689633 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.0985. Min Act: -0.1700
Data Index: 1624066 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.0985. Min Act: -0.1700
Data Index: 4824079 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.0985. Min Act: -0.1700
Data Index: 7631972 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.1297. Min Act: -0.1700
Data Index: 266696 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.0985. Min Act: -0.1700
Data Index: 5836890 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.0360. Min Act: -0.1700
Data Index: 620562 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7548. Min Range: -4.7548
Max Act: 4.0360. Min Act: -0.1700
Data Index: 789349 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7548. Min Range: -4.7548
Max Act: 3.9735. Min Act: -0.1700
Data Index: 289773 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19