Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4915 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.0389. Min Range: -13.0389
Max Act: 13.0389. Min Act: -0.1700
Data Index: 2949793 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.4764. Min Act: -0.1700
Data Index: 247881 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.4139. Min Act: -0.1700
Data Index: 2837151 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.4139. Min Act: -0.1700
Data Index: 3842141 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.3514. Min Act: -0.1700
Data Index: 3090813 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.2889. Min Act: -0.1700
Data Index: 46301 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.2889. Min Act: -0.1700
Data Index: 857519 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.2264. Min Act: -0.1700
Data Index: 2989406 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.2264. Min Act: -0.1700
Data Index: 1138455 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.2264. Min Act: -0.1700
Data Index: 8750822 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.2264. Min Act: -0.1700
Data Index: 6762758 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.1639. Min Act: -0.1700
Data Index: 3634308 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.2264. Min Act: -0.1700
Data Index: 3938364 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.1014. Min Act: -0.1700
Data Index: 7843658 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.1639. Min Act: -0.1700
Data Index: 4264332 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.1014. Min Act: -0.1700
Data Index: 2616637 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.1014. Min Act: -0.1700
Data Index: 5788670 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.1014. Min Act: -0.1700
Data Index: 6319432 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.1014. Min Act: -0.1700
Data Index: 364604 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.0389. Min Range: -13.0389
Max Act: 12.0389. Min Act: -0.1700
Data Index: 4580003 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19