Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5678 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.5933. Min Act: -0.1700
Data Index: 5772509 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.4683. Min Act: -0.1700
Data Index: 3162096 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.4370. Min Act: -0.1700
Data Index: 8316331 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.3120. Min Act: -0.1700
Data Index: 7072897 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.3433. Min Act: -0.1700
Data Index: 6564780 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.3433. Min Act: -0.1700
Data Index: 8701086 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.3120. Min Act: -0.1700
Data Index: 2785393 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.2495. Min Act: -0.1700
Data Index: 7280479 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.2495. Min Act: -0.1700
Data Index: 3804919 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.2183. Min Act: -0.1700
Data Index: 4938686 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.1558. Min Act: -0.1700
Data Index: 5807571 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.1558. Min Act: -0.1700
Data Index: 1595198 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.1558. Min Act: -0.1700
Data Index: 5988972 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.1558. Min Act: -0.1700
Data Index: 89710 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.0933. Min Act: -0.1700
Data Index: 5962874 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.0933. Min Act: -0.1700
Data Index: 1932473 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.0933. Min Act: -0.1700
Data Index: 7275204 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.0308. Min Act: -0.1700
Data Index: 7380062 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5933. Min Range: -6.5933
Max Act: 6.0620. Min Act: -0.1700
Data Index: 6932387 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5933. Min Range: -6.5933
Max Act: 5.9995. Min Act: -0.1700
Data Index: 5948453 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19