Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2156 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.5170. Min Act: -0.1700
Data Index: 1976461 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.5170. Min Act: -0.1700
Data Index: 1582577 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.4857. Min Act: -0.1700
Data Index: 1493871 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.4857. Min Act: -0.1700
Data Index: 4107403 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.3607. Min Act: -0.1700
Data Index: 2969279 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.3920. Min Act: -0.1700
Data Index: 1592222 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.3295. Min Act: -0.1700
Data Index: 6032318 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.3295. Min Act: -0.1700
Data Index: 7875906 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.3607. Min Act: -0.1700
Data Index: 1002015 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.2670. Min Act: -0.1700
Data Index: 6879526 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.2982. Min Act: -0.1700
Data Index: 6154285 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.2357. Min Act: -0.1700
Data Index: 5915303 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.2357. Min Act: -0.1700
Data Index: 2207904 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.2670. Min Act: -0.1700
Data Index: 3348858 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.2357. Min Act: -0.1700
Data Index: 3874510 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.2357. Min Act: -0.1700
Data Index: 2109811 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.2357. Min Act: -0.1700
Data Index: 137040 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.2357. Min Act: -0.1700
Data Index: 1464566 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.2357. Min Act: -0.1700
Data Index: 6592802 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5170. Min Range: -5.5170
Max Act: 5.2357. Min Act: -0.1700
Data Index: 879720 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19