Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2899 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3378. Min Range: -11.3378
Max Act: 11.3378. Min Act: -0.1700
Data Index: 2209040 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3378. Min Range: -11.3378
Max Act: 11.1503. Min Act: -0.1700
Data Index: 253722 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3378. Min Range: -11.3378
Max Act: 11.1503. Min Act: -0.1700
Data Index: 5132880 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.9003. Min Act: -0.1700
Data Index: 1741177 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.8378. Min Act: -0.1700
Data Index: 7078306 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.7753. Min Act: -0.1700
Data Index: 7206281 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.7128. Min Act: -0.1700
Data Index: 5700265 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.5878. Min Act: -0.1700
Data Index: 7133357 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.7128. Min Act: -0.1700
Data Index: 6163951 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.5878. Min Act: -0.1700
Data Index: 7390518 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.4628. Min Act: -0.1700
Data Index: 5912419 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.4003. Min Act: -0.1700
Data Index: 4817556 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.4003. Min Act: -0.1700
Data Index: 1200779 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.2753. Min Act: -0.1700
Data Index: 2217088 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.2753. Min Act: -0.1700
Data Index: 8600670 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.2753. Min Act: -0.1700
Data Index: 600924 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.2753. Min Act: -0.1700
Data Index: 2743307 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.2128. Min Act: -0.1700
Data Index: 2159816 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.2128. Min Act: -0.1700
Data Index: 1591914 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3378. Min Range: -11.3378
Max Act: 10.2128. Min Act: -0.1700
Data Index: 3227461 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19