Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2956 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.6469. Min Act: -0.1700
Data Index: 8557519 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.5219. Min Act: -0.1700
Data Index: 6458583 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.4594. Min Act: -0.1700
Data Index: 5214246 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.4594. Min Act: -0.1700
Data Index: 7080584 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.4594. Min Act: -0.1700
Data Index: 8739949 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.3032. Min Act: -0.1700
Data Index: 7139982 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.2407. Min Act: -0.1700
Data Index: 1398023 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.2094. Min Act: -0.1700
Data Index: 4175770 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.2407. Min Act: -0.1700
Data Index: 984495 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.1782. Min Act: -0.1700
Data Index: 4611397 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.1469. Min Act: -0.1700
Data Index: 5437783 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.1469. Min Act: -0.1700
Data Index: 1665660 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.1469. Min Act: -0.1700
Data Index: 2685719 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.0844. Min Act: -0.1700
Data Index: 3413208 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.0532. Min Act: -0.1700
Data Index: 4158448 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.0219. Min Act: -0.1700
Data Index: 7660725 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6469. Min Range: -5.6469
Max Act: 4.9907. Min Act: -0.1700
Data Index: 235770 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6469. Min Range: -5.6469
Max Act: 4.9907. Min Act: -0.1700
Data Index: 4386517 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6469. Min Range: -5.6469
Max Act: 4.9594. Min Act: -0.1700
Data Index: 7007522 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6469. Min Range: -5.6469
Max Act: 4.9594. Min Act: -0.1700
Data Index: 3117864 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19