Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.9750. Min Act: -0.1700
Data Index: 3676198 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.8812. Min Act: -0.1700
Data Index: 8480923 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.8500. Min Act: -0.1700
Data Index: 6141542 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.8500. Min Act: -0.1700
Data Index: 3070092 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.8187. Min Act: -0.1700
Data Index: 6352420 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.7875. Min Act: -0.1700
Data Index: 7626162 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.7875. Min Act: -0.1700
Data Index: 4843391 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.7875. Min Act: -0.1700
Data Index: 4806406 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.8187. Min Act: -0.1700
Data Index: 3331190 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.7562. Min Act: -0.1700
Data Index: 8449452 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.6937. Min Act: -0.1700
Data Index: 1026876 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.7250. Min Act: -0.1699
Data Index: 2060845 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.7250. Min Act: -0.1700
Data Index: 6352415 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.6625. Min Act: -0.1700
Data Index: 6845099 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.6937. Min Act: -0.1700
Data Index: 6888440 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.6625. Min Act: -0.1700
Data Index: 4617717 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.6625. Min Act: -0.1700
Data Index: 6352416 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.6625. Min Act: -0.1700
Data Index: 7883809 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.6312. Min Act: -0.1700
Data Index: 2762068 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9750. Min Range: -5.9750
Max Act: 5.6625. Min Act: -0.1700
Data Index: 2503536 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19