Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1514 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.6669. Min Act: -0.1700
Data Index: 7401637 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.6356. Min Act: -0.1700
Data Index: 5151891 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.5731. Min Act: -0.1700
Data Index: 4735345 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.5419. Min Act: -0.1700
Data Index: 5594303 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.5419. Min Act: -0.1700
Data Index: 392554 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.5419. Min Act: -0.1700
Data Index: 5476837 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.5419. Min Act: -0.1700
Data Index: 7074051 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.5419. Min Act: -0.1700
Data Index: 3200485 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.5419. Min Act: -0.1700
Data Index: 697331 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.5106. Min Act: -0.1700
Data Index: 2002703 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.5106. Min Act: -0.1700
Data Index: 5345626 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.4481. Min Act: -0.1700
Data Index: 1500747 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.4169. Min Act: -0.1700
Data Index: 6516511 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.3544. Min Act: -0.1700
Data Index: 2263407 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.3544. Min Act: -0.1700
Data Index: 445178 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.3544. Min Act: -0.1700
Data Index: 1289491 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.3544. Min Act: -0.1700
Data Index: 2127977 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.3231. Min Act: -0.1700
Data Index: 5182981 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.2919. Min Act: -0.1700
Data Index: 1461717 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6669. Min Range: -5.6669
Max Act: 5.2919. Min Act: -0.1700
Data Index: 5874081 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19