Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4875 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5751. Min Range: -6.5751
Max Act: 6.5751. Min Act: -0.1700
Data Index: 5029670 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5751. Min Range: -6.5751
Max Act: 6.1063. Min Act: -0.1700
Data Index: 7667325 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5751. Min Range: -6.5751
Max Act: 6.0438. Min Act: -0.1700
Data Index: 6641255 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.9188. Min Act: -0.1700
Data Index: 6353812 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.9188. Min Act: -0.1700
Data Index: 77925 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.8876. Min Act: -0.1700
Data Index: 7303266 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.8563. Min Act: -0.1700
Data Index: 5927482 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.8563. Min Act: -0.1700
Data Index: 4253147 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.8251. Min Act: -0.1700
Data Index: 3666791 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.8251. Min Act: -0.1700
Data Index: 4119033 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.7938. Min Act: -0.1700
Data Index: 130493 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.7938. Min Act: -0.1700
Data Index: 2982625 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.7626. Min Act: -0.1700
Data Index: 4394765 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.7626. Min Act: -0.1700
Data Index: 2182151 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.7313. Min Act: -0.1700
Data Index: 6066324 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.7001. Min Act: -0.1700
Data Index: 4862312 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.7001. Min Act: -0.1700
Data Index: 464339 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.7001. Min Act: -0.1700
Data Index: 7658710 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.7001. Min Act: -0.1700
Data Index: 565527 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5751. Min Range: -6.5751
Max Act: 5.7001. Min Act: -0.1700
Data Index: 5558583 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19