Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4932 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0284. Min Range: -7.0284
Max Act: 7.0284. Min Act: -0.1700
Data Index: 837438 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.9971. Min Act: -0.1700
Data Index: 1432704 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.8409. Min Act: -0.1700
Data Index: 3549502 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.7784. Min Act: -0.1700
Data Index: 8514335 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.7471. Min Act: -0.1700
Data Index: 4657610 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.7159. Min Act: -0.1700
Data Index: 1672207 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.6846. Min Act: -0.1700
Data Index: 837439 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.6846. Min Act: -0.1700
Data Index: 1201921 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.6534. Min Act: -0.1700
Data Index: 2422284 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.6534. Min Act: -0.1700
Data Index: 3034781 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.6221. Min Act: -0.1700
Data Index: 777548 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.5909. Min Act: -0.1700
Data Index: 600359 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.5909. Min Act: -0.1700
Data Index: 3256554 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.6221. Min Act: -0.1700
Data Index: 1633642 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.5909. Min Act: -0.1700
Data Index: 4302887 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.5596. Min Act: -0.1700
Data Index: 2732337 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.4971. Min Act: -0.1700
Data Index: 5789449 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.5284. Min Act: -0.1700
Data Index: 5964633 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.4971. Min Act: -0.1700
Data Index: 8483014 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0284. Min Range: -7.0284
Max Act: 6.4971. Min Act: -0.1700
Data Index: 5690088 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19