Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2893 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1270. Min Range: -6.1270
Max Act: 6.1270. Min Act: -0.1700
Data Index: 6152079 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1270. Min Range: -6.1270
Max Act: 6.0332. Min Act: -0.1700
Data Index: 6755846 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1270. Min Range: -6.1270
Max Act: 6.0020. Min Act: -0.1700
Data Index: 3040478 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1270. Min Range: -6.1270
Max Act: 6.0332. Min Act: -0.1700
Data Index: 3869260 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1270. Min Range: -6.1270
Max Act: 6.0020. Min Act: -0.1700
Data Index: 5363579 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1270. Min Range: -6.1270
Max Act: 5.9707. Min Act: -0.1700
Data Index: 1217919 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1270. Min Range: -6.1270
Max Act: 5.9395. Min Act: -0.1700
Data Index: 7980925 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1270. Min Range: -6.1270
Max Act: 5.9395. Min Act: -0.1700
Data Index: 8433306 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1270. Min Range: -6.1270
Max Act: 5.9082. Min Act: -0.1700
Data Index: 935672 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1270. Min Range: -6.1270
Max Act: 5.8770. Min Act: -0.1700
Data Index: 5039453 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1270. Min Range: -6.1270
Max Act: 5.8770. Min Act: -0.1700
Data Index: 8224953 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1270. Min Range: -6.1270
Max Act: 5.8457. Min Act: -0.1700
Data Index: 1417062 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1270. Min Range: -6.1270
Max Act: 5.8457. Min Act: -0.1700
Data Index: 8294530 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1270. Min Range: -6.1270
Max Act: 5.8145. Min Act: -0.1700
Data Index: 3613786 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1270. Min Range: -6.1270
Max Act: 5.7832. Min Act: -0.1700
Data Index: 8088291 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1270. Min Range: -6.1270
Max Act: 5.7832. Min Act: -0.1700
Data Index: 8581058 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1270. Min Range: -6.1270
Max Act: 5.7520. Min Act: -0.1700
Data Index: 4444279 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1270. Min Range: -6.1270
Max Act: 5.7207. Min Act: -0.1700
Data Index: 160471 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1270. Min Range: -6.1270
Max Act: 5.7207. Min Act: -0.1700
Data Index: 2839734 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1270. Min Range: -6.1270
Max Act: 5.7207. Min Act: -0.1700
Data Index: 5738615 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19