Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6195 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.9887. Min Act: -0.1649
Data Index: 8454028 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.9887. Min Act: -0.1693
Data Index: 8454026 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.9262. Min Act: -0.1700
Data Index: 8454029 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.8012. Min Act: -0.1700
Data Index: 7828912 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.7699. Min Act: -0.1699
Data Index: 3629695 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.7387. Min Act: -0.1699
Data Index: 5121202 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.7074. Min Act: -0.1699
Data Index: 6564311 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.6449. Min Act: -0.1700
Data Index: 2579891 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.5199. Min Act: -0.1419
Data Index: 267200 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.4887. Min Act: -0.1624
Data Index: 6564312 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.4574. Min Act: -0.1694
Data Index: 8095735 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.4262. Min Act: -0.1699
Data Index: 4188032 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.4262. Min Act: -0.1700
Data Index: 4140100 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.4262. Min Act: -0.1700
Data Index: 1867770 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.3949. Min Act: -0.1700
Data Index: 6463520 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.3949. Min Act: -0.1700
Data Index: 986736 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.3637. Min Act: -0.1700
Data Index: 6657025 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.3637. Min Act: -0.1700
Data Index: 6105640 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.3324. Min Act: -0.1700
Data Index: 7730747 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9887. Min Range: -6.9887
Max Act: 6.3637. Min Act: -0.1700
Data Index: 7752843 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19