Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1721 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.6600. Min Act: -0.1700
Data Index: 447888 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.6287. Min Act: -0.1700
Data Index: 5361233 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.6287. Min Act: -0.1700
Data Index: 1863657 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5974. Min Act: -0.1700
Data Index: 7961466 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5974. Min Act: -0.1699
Data Index: 5837315 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5661. Min Act: -0.1700
Data Index: 5072160 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5661. Min Act: -0.1700
Data Index: 4715342 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5348. Min Act: -0.1700
Data Index: 5829496 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5348. Min Act: -0.1700
Data Index: 3301850 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5348. Min Act: -0.1700
Data Index: 3460666 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5035. Min Act: -0.1700
Data Index: 4837194 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5035. Min Act: -0.1700
Data Index: 3153428 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5035. Min Act: -0.1700
Data Index: 6195341 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5035. Min Act: -0.1700
Data Index: 2020590 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5035. Min Act: -0.1700
Data Index: 1861252 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5035. Min Act: -0.1700
Data Index: 1567785 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5035. Min Act: -0.1700
Data Index: 2187553 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.5035. Min Act: -0.1700
Data Index: 1340517 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.4721. Min Act: -0.1700
Data Index: 4559748 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6600. Min Range: -3.6600
Max Act: 3.4721. Min Act: -0.1700
Data Index: 1478383 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19