Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4186 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.9804. Min Act: -0.1700
Data Index: 3479023 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.5429. Min Act: -0.1700
Data Index: 1154603 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.4492. Min Act: -0.1700
Data Index: 8374392 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.4492. Min Act: -0.1700
Data Index: 873025 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.4492. Min Act: -0.1700
Data Index: 4642931 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.3554. Min Act: -0.1700
Data Index: 2605775 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.3867. Min Act: -0.1700
Data Index: 6091156 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.3554. Min Act: -0.1700
Data Index: 92757 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.2929. Min Act: -0.1700
Data Index: 8272362 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.2929. Min Act: -0.1700
Data Index: 6281298 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.3242. Min Act: -0.1700
Data Index: 8089617 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.3242. Min Act: -0.1700
Data Index: 4704421 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.2929. Min Act: -0.1700
Data Index: 2485397 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.2929. Min Act: -0.1700
Data Index: 3457337 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.2617. Min Act: -0.1700
Data Index: 3537745 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.2929. Min Act: -0.1700
Data Index: 6690299 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.2617. Min Act: -0.1700
Data Index: 1394232 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.2617. Min Act: -0.1700
Data Index: 8097107 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.2304. Min Act: -0.1700
Data Index: 2200009 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9804. Min Range: -5.9804
Max Act: 5.2304. Min Act: -0.1700
Data Index: 6430060 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19