Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2163 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.5968. Min Act: -0.1700
Data Index: 4293936 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.5968. Min Act: -0.1700
Data Index: 3558524 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.5343. Min Act: -0.1700
Data Index: 7788549 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.5343. Min Act: -0.1700
Data Index: 764354 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.5343. Min Act: -0.1700
Data Index: 8420416 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.5031. Min Act: -0.1700
Data Index: 6212341 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.5031. Min Act: -0.1700
Data Index: 4521733 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.5031. Min Act: -0.1700
Data Index: 4100046 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.5031. Min Act: -0.1700
Data Index: 8147462 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.4718. Min Act: -0.1700
Data Index: 4471309 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.4718. Min Act: -0.1700
Data Index: 3107681 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.4718. Min Act: -0.1700
Data Index: 5404088 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.4718. Min Act: -0.1700
Data Index: 7890092 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.4406. Min Act: -0.1700
Data Index: 2529694 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.4093. Min Act: -0.1700
Data Index: 5973317 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.4718. Min Act: -0.1700
Data Index: 4155816 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.4406. Min Act: -0.1700
Data Index: 5827390 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.4406. Min Act: -0.1700
Data Index: 594536 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.4406. Min Act: -0.1700
Data Index: 6136981 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5968. Min Range: -5.5968
Max Act: 5.3781. Min Act: -0.1700
Data Index: 6131711 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19