Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4886 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.7750. Min Act: -0.1700
Data Index: 5342351 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.7750. Min Act: -0.1700
Data Index: 2356184 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.7125. Min Act: -0.1700
Data Index: 1184123 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.7438. Min Act: -0.1700
Data Index: 7513938 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.7438. Min Act: -0.1700
Data Index: 827302 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.6500. Min Act: -0.1700
Data Index: 5867471 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.6500. Min Act: -0.1700
Data Index: 3490481 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.5875. Min Act: -0.1700
Data Index: 4761791 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.5875. Min Act: -0.1700
Data Index: 1203859 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.5563. Min Act: -0.1700
Data Index: 2595367 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.5563. Min Act: -0.1700
Data Index: 563426 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.5563. Min Act: -0.1700
Data Index: 543569 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.5250. Min Act: -0.1700
Data Index: 5709451 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.4938. Min Act: -0.1700
Data Index: 5172416 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.4625. Min Act: -0.1700
Data Index: 4451071 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.4625. Min Act: -0.1700
Data Index: 8561875 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.4313. Min Act: -0.1700
Data Index: 4797789 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.4313. Min Act: -0.1700
Data Index: 7055526 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.4313. Min Act: -0.1700
Data Index: 6990420 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7750. Min Range: -6.7750
Max Act: 6.4000. Min Act: -0.1700
Data Index: 3849502 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19