Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3947 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0805. Min Range: -11.0805
Max Act: 11.0805. Min Act: -0.1700
Data Index: 3798880 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.7055. Min Act: -0.1700
Data Index: 4200189 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.7055. Min Act: -0.1700
Data Index: 8052589 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.7055. Min Act: -0.1700
Data Index: 6991303 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.4555. Min Act: -0.1700
Data Index: 750540 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.3305. Min Act: -0.1700
Data Index: 2797090 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.3305. Min Act: -0.1700
Data Index: 3394859 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.3305. Min Act: -0.1700
Data Index: 8052582 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.3305. Min Act: -0.1700
Data Index: 8301107 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.3305. Min Act: -0.1700
Data Index: 2511820 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.2680. Min Act: -0.1700
Data Index: 7396235 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.2680. Min Act: -0.1700
Data Index: 2801030 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.2680. Min Act: -0.1700
Data Index: 3640456 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.2680. Min Act: -0.1700
Data Index: 5859847 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.2680. Min Act: -0.1700
Data Index: 6612615 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.2055. Min Act: -0.1700
Data Index: 5072002 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.2055. Min Act: -0.1700
Data Index: 1486869 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.2680. Min Act: -0.1700
Data Index: 1485183 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.2055. Min Act: -0.1700
Data Index: 3179291 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0805. Min Range: -11.0805
Max Act: 10.1430. Min Act: -0.1700
Data Index: 5390290 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19