Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 667 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.9309. Min Act: -0.1700
Data Index: 6371031 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.8997. Min Act: -0.1700
Data Index: 4696365 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.8997. Min Act: -0.1700
Data Index: 1316410 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.8684. Min Act: -0.1700
Data Index: 819133 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.8059. Min Act: -0.1700
Data Index: 5253762 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.8372. Min Act: -0.1700
Data Index: 1703422 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.8372. Min Act: -0.1700
Data Index: 8270427 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.8372. Min Act: -0.1700
Data Index: 3729570 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.8372. Min Act: -0.1700
Data Index: 620729 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.8059. Min Act: -0.1700
Data Index: 819156 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.8059. Min Act: -0.1700
Data Index: 1827087 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.7122. Min Act: -0.1700
Data Index: 6608469 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.7122. Min Act: -0.1700
Data Index: 2317139 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.7122. Min Act: -0.1700
Data Index: 5296133 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.6184. Min Act: -0.1700
Data Index: 4584229 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.6184. Min Act: -0.1700
Data Index: 2663083 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.6184. Min Act: -0.1700
Data Index: 354620 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.6184. Min Act: -0.1700
Data Index: 998922 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.6184. Min Act: -0.1700
Data Index: 568914 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9309. Min Range: -6.9309
Max Act: 6.5872. Min Act: -0.1700
Data Index: 287218 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19