Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2579 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.8609. Min Act: -0.1700
Data Index: 1242252 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.7984. Min Act: -0.1700
Data Index: 4676501 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.6734. Min Act: -0.1700
Data Index: 1402005 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.6109. Min Act: -0.1700
Data Index: 5333702 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.5484. Min Act: -0.1700
Data Index: 439731 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.2984. Min Act: -0.1700
Data Index: 3082385 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.3609. Min Act: -0.1700
Data Index: 5242247 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.3609. Min Act: -0.1700
Data Index: 4134075 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.3609. Min Act: -0.1700
Data Index: 5051676 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.3609. Min Act: -0.1700
Data Index: 4803273 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.2359. Min Act: -0.1700
Data Index: 963111 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.2359. Min Act: -0.1700
Data Index: 230193 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.1734. Min Act: -0.1700
Data Index: 7187647 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.2359. Min Act: -0.1700
Data Index: 8207380 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.2359. Min Act: -0.1700
Data Index: 6630513 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.2359. Min Act: -0.1700
Data Index: 7199165 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.2359. Min Act: -0.1700
Data Index: 2910187 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.2359. Min Act: -0.1700
Data Index: 7704402 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.1734. Min Act: -0.1700
Data Index: 2841691 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8609. Min Range: -8.8609
Max Act: 8.1734. Min Act: -0.1700
Data Index: 444407 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19