Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2314 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3338. Min Range: -5.3338
Max Act: 5.3338. Min Act: -0.1700
Data Index: 5475842 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3338. Min Range: -5.3338
Max Act: 5.2088. Min Act: -0.1700
Data Index: 249514 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3338. Min Range: -5.3338
Max Act: 5.1775. Min Act: -0.1700
Data Index: 7943413 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3338. Min Range: -5.3338
Max Act: 5.1150. Min Act: -0.1700
Data Index: 4942167 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3338. Min Range: -5.3338
Max Act: 5.1150. Min Act: -0.1700
Data Index: 7820010 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3338. Min Range: -5.3338
Max Act: 4.9588. Min Act: -0.1700
Data Index: 48089 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3338. Min Range: -5.3338
Max Act: 4.8963. Min Act: -0.1700
Data Index: 5560876 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3338. Min Range: -5.3338
Max Act: 4.8025. Min Act: -0.1700
Data Index: 8469 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3338. Min Range: -5.3338
Max Act: 4.7400. Min Act: -0.1700
Data Index: 3547902 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3338. Min Range: -5.3338
Max Act: 4.7713. Min Act: -0.1700
Data Index: 6495384 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3338. Min Range: -5.3338
Max Act: 4.6463. Min Act: -0.1700
Data Index: 7176870 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3338. Min Range: -5.3338
Max Act: 4.6150. Min Act: -0.1700
Data Index: 6884678 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3338. Min Range: -5.3338
Max Act: 4.5838. Min Act: -0.1700
Data Index: 5822402 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3338. Min Range: -5.3338
Max Act: 4.5838. Min Act: -0.1700
Data Index: 4977081 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3338. Min Range: -5.3338
Max Act: 4.5525. Min Act: -0.1700
Data Index: 6766625 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3338. Min Range: -5.3338
Max Act: 4.5213. Min Act: -0.1700
Data Index: 6259789 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3338. Min Range: -5.3338
Max Act: 4.5525. Min Act: -0.1700
Data Index: 6307051 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3338. Min Range: -5.3338
Max Act: 4.5213. Min Act: -0.1700
Data Index: 1763536 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3338. Min Range: -5.3338
Max Act: 4.4900. Min Act: -0.1700
Data Index: 7223581 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3338. Min Range: -5.3338
Max Act: 4.4588. Min Act: -0.1700
Data Index: 513303 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19