Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1155 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6204. Min Range: -7.6204
Max Act: 7.6204. Min Act: -0.1700
Data Index: 4903994 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6204. Min Range: -7.6204
Max Act: 7.4641. Min Act: -0.1700
Data Index: 8675518 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6204. Min Range: -7.6204
Max Act: 7.3704. Min Act: -0.1700
Data Index: 7758765 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6204. Min Range: -7.6204
Max Act: 7.2454. Min Act: -0.1700
Data Index: 3512266 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6204. Min Range: -7.6204
Max Act: 7.2141. Min Act: -0.1700
Data Index: 5467929 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6204. Min Range: -7.6204
Max Act: 7.1829. Min Act: -0.1700
Data Index: 7415612 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6204. Min Range: -7.6204
Max Act: 7.1516. Min Act: -0.1700
Data Index: 6955277 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6204. Min Range: -7.6204
Max Act: 7.0891. Min Act: -0.1700
Data Index: 3687859 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6204. Min Range: -7.6204
Max Act: 7.0891. Min Act: -0.1700
Data Index: 3788769 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6204. Min Range: -7.6204
Max Act: 7.0891. Min Act: -0.1700
Data Index: 8489992 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6204. Min Range: -7.6204
Max Act: 7.0579. Min Act: -0.1700
Data Index: 5002872 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6204. Min Range: -7.6204
Max Act: 7.0266. Min Act: -0.1700
Data Index: 6040950 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6204. Min Range: -7.6204
Max Act: 7.0266. Min Act: -0.1700
Data Index: 5829815 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6204. Min Range: -7.6204
Max Act: 7.0266. Min Act: -0.1700
Data Index: 1780551 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6204. Min Range: -7.6204
Max Act: 6.9954. Min Act: -0.1700
Data Index: 1630317 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6204. Min Range: -7.6204
Max Act: 6.9329. Min Act: -0.1700
Data Index: 791093 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6204. Min Range: -7.6204
Max Act: 6.9329. Min Act: -0.1700
Data Index: 6156217 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6204. Min Range: -7.6204
Max Act: 6.9016. Min Act: -0.1700
Data Index: 5813983 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6204. Min Range: -7.6204
Max Act: 6.8704. Min Act: -0.1700
Data Index: 1257449 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6204. Min Range: -7.6204
Max Act: 6.9016. Min Act: -0.1700
Data Index: 5955848 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19