Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4018 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.6470. Min Act: -0.1700
Data Index: 6865729 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.4121. Min Act: -0.1700
Data Index: 2695235 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.3494. Min Act: -0.1700
Data Index: 7201893 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.3023. Min Act: -0.1700
Data Index: 6495077 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.2866. Min Act: -0.1700
Data Index: 3916363 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.2866. Min Act: -0.1700
Data Index: 7388900 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.2080. Min Act: -0.1700
Data Index: 8708709 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.2080. Min Act: -0.1700
Data Index: 3722904 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.1923. Min Act: -0.1700
Data Index: 1469473 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.1923. Min Act: -0.1700
Data Index: 6807859 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.1923. Min Act: -0.1700
Data Index: 1290184 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.1923. Min Act: -0.1700
Data Index: 6039192 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.1608. Min Act: -0.1700
Data Index: 6719023 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.1766. Min Act: -0.1700
Data Index: 863601 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.1608. Min Act: -0.1700
Data Index: 5632024 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.1766. Min Act: -0.1700
Data Index: 6971752 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.1451. Min Act: -0.1700
Data Index: 172570 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.1608. Min Act: -0.1700
Data Index: 4922112 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.1608. Min Act: -0.1700
Data Index: 6395699 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6470. Min Range: -3.6470
Max Act: 3.1608. Min Act: -0.1700
Data Index: 2486550 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19