Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6864. Min Range: -7.6864
Max Act: 7.6864. Min Act: -0.1700
Data Index: 1030534 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6864. Min Range: -7.6864
Max Act: 7.3114. Min Act: -0.1700
Data Index: 2152964 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6864. Min Range: -7.6864
Max Act: 7.2489. Min Act: -0.1700
Data Index: 8345657 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6864. Min Range: -7.6864
Max Act: 7.0926. Min Act: -0.1700
Data Index: 1680450 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6864. Min Range: -7.6864
Max Act: 7.0301. Min Act: -0.1700
Data Index: 7361746 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6864. Min Range: -7.6864
Max Act: 6.9989. Min Act: -0.1700
Data Index: 6273455 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6864. Min Range: -7.6864
Max Act: 6.9676. Min Act: -0.1700
Data Index: 651854 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6864. Min Range: -7.6864
Max Act: 6.8739. Min Act: -0.1700
Data Index: 2923338 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6864. Min Range: -7.6864
Max Act: 6.9051. Min Act: -0.1700
Data Index: 3249282 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6864. Min Range: -7.6864
Max Act: 6.8739. Min Act: -0.1700
Data Index: 5569934 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6864. Min Range: -7.6864
Max Act: 6.8739. Min Act: -0.1700
Data Index: 2244723 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6864. Min Range: -7.6864
Max Act: 6.8739. Min Act: -0.1700
Data Index: 1895198 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6864. Min Range: -7.6864
Max Act: 6.8426. Min Act: -0.1700
Data Index: 7461778 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6864. Min Range: -7.6864
Max Act: 6.8426. Min Act: -0.1700
Data Index: 8314580 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6864. Min Range: -7.6864
Max Act: 6.7801. Min Act: -0.1700
Data Index: 7418186 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6864. Min Range: -7.6864
Max Act: 6.7801. Min Act: -0.1700
Data Index: 8725062 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6864. Min Range: -7.6864
Max Act: 6.7801. Min Act: -0.1700
Data Index: 2023347 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6864. Min Range: -7.6864
Max Act: 6.7801. Min Act: -0.1700
Data Index: 8725074 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6864. Min Range: -7.6864
Max Act: 6.7489. Min Act: -0.1700
Data Index: 6772997 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6864. Min Range: -7.6864
Max Act: 6.7489. Min Act: -0.1700
Data Index: 4169286 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19