Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.4270. Min Act: -0.1700
Data Index: 3286469 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.4270. Min Act: -0.1700
Data Index: 4403616 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.2395. Min Act: -0.1700
Data Index: 5122091 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.2395. Min Act: -0.1700
Data Index: 3982018 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.2395. Min Act: -0.1700
Data Index: 927800 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.2082. Min Act: -0.1700
Data Index: 5567198 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.2082. Min Act: -0.1700
Data Index: 2761064 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.1770. Min Act: -0.1700
Data Index: 15102 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.1457. Min Act: -0.1700
Data Index: 7667034 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.1145. Min Act: -0.1700
Data Index: 4472869 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.1457. Min Act: -0.1700
Data Index: 1053742 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.1457. Min Act: -0.1700
Data Index: 8333485 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.1457. Min Act: -0.1700
Data Index: 2614533 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.1457. Min Act: -0.1700
Data Index: 4672599 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.1145. Min Act: -0.1700
Data Index: 6316792 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.1145. Min Act: -0.1700
Data Index: 2455270 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.1145. Min Act: -0.1700
Data Index: 644124 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.1457. Min Act: -0.1700
Data Index: 6471771 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.1145. Min Act: -0.1700
Data Index: 7478498 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4270. Min Range: -5.4270
Max Act: 5.0832. Min Act: -0.1700
Data Index: 7635359 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19