Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5344 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.9585. Min Act: -0.1700
Data Index: 1809839 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.8475. Min Act: -0.1700
Data Index: 4334643 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.8475. Min Act: -0.1700
Data Index: 2073078 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.8157. Min Act: -0.1700
Data Index: 1188254 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7998. Min Act: -0.1700
Data Index: 6559066 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7998. Min Act: -0.1700
Data Index: 2474635 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7998. Min Act: -0.1700
Data Index: 5751572 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7998. Min Act: -0.1700
Data Index: 7270797 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7838. Min Act: -0.1700
Data Index: 721771 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7838. Min Act: -0.1700
Data Index: 1891150 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7679. Min Act: -0.1700
Data Index: 3242711 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7679. Min Act: -0.1700
Data Index: 1716723 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7679. Min Act: -0.1700
Data Index: 3029627 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7679. Min Act: -0.1700
Data Index: 8182294 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7360. Min Act: -0.1700
Data Index: 3854398 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7519. Min Act: -0.1700
Data Index: 7499559 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7200. Min Act: -0.1700
Data Index: 8012383 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7200. Min Act: -0.1700
Data Index: 8017273 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7200. Min Act: -0.1700
Data Index: 6526299 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9585. Min Range: -2.9585
Max Act: 2.7360. Min Act: -0.1700
Data Index: 2113728 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19