Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2831 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.8428. Min Act: -0.1700
Data Index: 3503407 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.7472. Min Act: -0.1699
Data Index: 3445552 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.7472. Min Act: -0.1700
Data Index: 3150372 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6992. Min Act: -0.1700
Data Index: 3344274 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6992. Min Act: -0.1700
Data Index: 6871202 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6992. Min Act: -0.1699
Data Index: 1280869 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6832. Min Act: -0.1700
Data Index: 1961476 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6832. Min Act: -0.1700
Data Index: 1859154 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6832. Min Act: -0.1700
Data Index: 5214125 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6672. Min Act: -0.1700
Data Index: 2456594 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6672. Min Act: -0.1700
Data Index: 7705591 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6512. Min Act: -0.1700
Data Index: 6638949 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6512. Min Act: -0.1700
Data Index: 8288450 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6512. Min Act: -0.1700
Data Index: 2901769 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6512. Min Act: -0.1700
Data Index: 4732067 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6512. Min Act: -0.1700
Data Index: 1828513 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6512. Min Act: -0.1700
Data Index: 6674133 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6351. Min Act: -0.1700
Data Index: 5658699 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6351. Min Act: -0.1700
Data Index: 2467160 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8428. Min Range: -2.8428
Max Act: 2.6351. Min Act: -0.1697
Data Index: 4734942 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19