Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2918 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1680. Min Range: -8.1680
Max Act: 8.1680. Min Act: -0.1700
Data Index: 5595801 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.9805. Min Act: -0.1700
Data Index: 97645 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.7930. Min Act: -0.1699
Data Index: 8656317 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.8555. Min Act: -0.1698
Data Index: 1242328 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.7305. Min Act: -0.1700
Data Index: 6867574 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.7305. Min Act: -0.1700
Data Index: 687096 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.7305. Min Act: -0.1700
Data Index: 1426132 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.7305. Min Act: -0.1700
Data Index: 2324147 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.6680. Min Act: -0.1700
Data Index: 6028237 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.6680. Min Act: -0.1700
Data Index: 967056 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.6055. Min Act: -0.1690
Data Index: 8779693 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.6055. Min Act: -0.1700
Data Index: 7552734 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.6055. Min Act: -0.1700
Data Index: 2103009 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.5430. Min Act: -0.1699
Data Index: 6055543 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.6055. Min Act: -0.1700
Data Index: 3768356 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.5430. Min Act: -0.1700
Data Index: 2045541 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.4805. Min Act: -0.1690
Data Index: 819708 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.4805. Min Act: -0.1697
Data Index: 3437297 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.4493. Min Act: -0.1700
Data Index: 8252751 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1680. Min Range: -8.1680
Max Act: 7.4493. Min Act: -0.1700
Data Index: 4706018 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19