Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4641 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1239. Min Range: -8.1239
Max Act: 8.1239. Min Act: -0.1700
Data Index: 2894436 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1239. Min Range: -8.1239
Max Act: 7.9676. Min Act: -0.1700
Data Index: 4046461 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1239. Min Range: -8.1239
Max Act: 7.7176. Min Act: -0.1700
Data Index: 7767600 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1239. Min Range: -8.1239
Max Act: 7.6864. Min Act: -0.1700
Data Index: 4008427 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1239. Min Range: -8.1239
Max Act: 7.6864. Min Act: -0.1700
Data Index: 5146996 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1239. Min Range: -8.1239
Max Act: 7.6239. Min Act: -0.1700
Data Index: 5510176 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1239. Min Range: -8.1239
Max Act: 7.5614. Min Act: -0.1700
Data Index: 1201543 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1239. Min Range: -8.1239
Max Act: 7.5614. Min Act: -0.1700
Data Index: 2345010 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1239. Min Range: -8.1239
Max Act: 7.4676. Min Act: -0.1700
Data Index: 6514245 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1239. Min Range: -8.1239
Max Act: 7.4051. Min Act: -0.1700
Data Index: 6179382 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1239. Min Range: -8.1239
Max Act: 7.3739. Min Act: -0.1700
Data Index: 5851072 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1239. Min Range: -8.1239
Max Act: 7.3426. Min Act: -0.1700
Data Index: 3757780 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1239. Min Range: -8.1239
Max Act: 7.1864. Min Act: -0.1700
Data Index: 4923299 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1239. Min Range: -8.1239
Max Act: 7.1551. Min Act: -0.1700
Data Index: 2168177 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1239. Min Range: -8.1239
Max Act: 7.1239. Min Act: -0.1700
Data Index: 7232805 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1239. Min Range: -8.1239
Max Act: 7.0926. Min Act: -0.1700
Data Index: 7597201 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1239. Min Range: -8.1239
Max Act: 6.8114. Min Act: -0.1700
Data Index: 767075 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1239. Min Range: -8.1239
Max Act: 6.7176. Min Act: -0.1700
Data Index: 4263414 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1239. Min Range: -8.1239
Max Act: 6.7176. Min Act: -0.1700
Data Index: 1555228 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1239. Min Range: -8.1239
Max Act: 6.6864. Min Act: -0.1700
Data Index: 4473736 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19