Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2767 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.9857. Min Act: -0.1700
Data Index: 890356 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.9545. Min Act: -0.1700
Data Index: 4671016 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.9857. Min Act: -0.1700
Data Index: 5099489 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.9545. Min Act: -0.1700
Data Index: 1332222 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.9232. Min Act: -0.1700
Data Index: 4682451 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.8607. Min Act: -0.1700
Data Index: 4235749 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.7982. Min Act: -0.1700
Data Index: 2630460 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.7045. Min Act: -0.1700
Data Index: 1042255 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6420. Min Act: -0.1700
Data Index: 2866362 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6732. Min Act: -0.1700
Data Index: 7825137 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6732. Min Act: -0.1700
Data Index: 3937059 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6420. Min Act: -0.1700
Data Index: 6693361 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6420. Min Act: -0.1700
Data Index: 1352957 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6420. Min Act: -0.1700
Data Index: 2641755 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6420. Min Act: -0.1700
Data Index: 8266555 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6420. Min Act: -0.1700
Data Index: 6268258 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6420. Min Act: -0.1700
Data Index: 5536336 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6107. Min Act: -0.1700
Data Index: 7844380 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6107. Min Act: -0.1700
Data Index: 2234409 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.5482. Min Act: -0.1700
Data Index: 5114692 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19