Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4146 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.8726. Min Act: -0.1700
Data Index: 6254576 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.8413. Min Act: -0.1700
Data Index: 7807395 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.8413. Min Act: -0.1700
Data Index: 6178513 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.8413. Min Act: -0.1700
Data Index: 1371611 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.8413. Min Act: -0.1700
Data Index: 6291464 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.8413. Min Act: -0.1700
Data Index: 3596820 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.8413. Min Act: -0.1700
Data Index: 1227295 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.8413. Min Act: -0.1700
Data Index: 6376954 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.8413. Min Act: -0.1700
Data Index: 6501495 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.8101. Min Act: -0.1700
Data Index: 6078194 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.8101. Min Act: -0.1700
Data Index: 5019400 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.8101. Min Act: -0.1700
Data Index: 4934987 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.8101. Min Act: -0.1700
Data Index: 7508732 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.7788. Min Act: -0.1700
Data Index: 3052940 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.8101. Min Act: -0.1700
Data Index: 1399675 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.7788. Min Act: -0.1700
Data Index: 6584532 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.7788. Min Act: -0.1700
Data Index: 1204017 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.7788. Min Act: -0.1700
Data Index: 1072532 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.7788. Min Act: -0.1700
Data Index: 8494098 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8726. Min Range: -4.8726
Max Act: 4.7476. Min Act: -0.1700
Data Index: 5751760 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19