Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 502 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.9232. Min Act: -0.1700
Data Index: 81200 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.7357. Min Act: -0.1700
Data Index: 446368 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.6732. Min Act: -0.1700
Data Index: 7841036 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.5482. Min Act: -0.1700
Data Index: 4893725 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.3607. Min Act: -0.1700
Data Index: 5148890 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.3607. Min Act: -0.1700
Data Index: 2004583 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.2357. Min Act: -0.1700
Data Index: 8713955 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.2357. Min Act: -0.1700
Data Index: 8251301 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.2357. Min Act: -0.1700
Data Index: 8824548 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.1732. Min Act: -0.1700
Data Index: 5180100 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.1732. Min Act: -0.1700
Data Index: 1995290 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.1107. Min Act: -0.1700
Data Index: 4170864 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.1107. Min Act: -0.1700
Data Index: 2197159 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.1107. Min Act: -0.1700
Data Index: 4170865 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.0482. Min Act: -0.1700
Data Index: 8313434 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.0482. Min Act: -0.1700
Data Index: 4619878 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.0482. Min Act: -0.1700
Data Index: 919473 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9232. Min Range: -9.9232
Max Act: 9.0482. Min Act: -0.1700
Data Index: 5965838 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9232. Min Range: -9.9232
Max Act: 8.9857. Min Act: -0.1700
Data Index: 3318953 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9232. Min Range: -9.9232
Max Act: 8.9857. Min Act: -0.1700
Data Index: 2119653 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19