Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8696. Min Range: -9.8696
Max Act: 9.8696. Min Act: -0.1700
Data Index: 287076 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8696. Min Range: -9.8696
Max Act: 9.2446. Min Act: -0.1700
Data Index: 599291 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8696. Min Range: -9.8696
Max Act: 9.2446. Min Act: -0.1700
Data Index: 2086651 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8696. Min Range: -9.8696
Max Act: 9.1821. Min Act: -0.1700
Data Index: 3869602 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8696. Min Range: -9.8696
Max Act: 9.1196. Min Act: -0.1700
Data Index: 1006456 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8696. Min Range: -9.8696
Max Act: 9.0571. Min Act: -0.1700
Data Index: 4936643 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8696. Min Range: -9.8696
Max Act: 8.9946. Min Act: -0.1700
Data Index: 1738661 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8696. Min Range: -9.8696
Max Act: 8.9321. Min Act: -0.1700
Data Index: 5664829 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8696. Min Range: -9.8696
Max Act: 8.9946. Min Act: -0.1700
Data Index: 624982 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8696. Min Range: -9.8696
Max Act: 8.8696. Min Act: -0.1700
Data Index: 3864716 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8696. Min Range: -9.8696
Max Act: 8.8696. Min Act: -0.1700
Data Index: 6131408 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8696. Min Range: -9.8696
Max Act: 8.8696. Min Act: -0.1700
Data Index: 4575694 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8696. Min Range: -9.8696
Max Act: 8.8696. Min Act: -0.1700
Data Index: 4060522 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8696. Min Range: -9.8696
Max Act: 8.8696. Min Act: -0.1700
Data Index: 3295953 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8696. Min Range: -9.8696
Max Act: 8.8696. Min Act: -0.1700
Data Index: 2965763 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8696. Min Range: -9.8696
Max Act: 8.8071. Min Act: -0.1700
Data Index: 115002 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8696. Min Range: -9.8696
Max Act: 8.6821. Min Act: -0.1700
Data Index: 4598471 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8696. Min Range: -9.8696
Max Act: 8.6196. Min Act: -0.1700
Data Index: 2194978 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8696. Min Range: -9.8696
Max Act: 8.6821. Min Act: -0.1700
Data Index: 269742 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8696. Min Range: -9.8696
Max Act: 8.6821. Min Act: -0.1700
Data Index: 2153983 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19