Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1312 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2871. Min Range: -9.2871
Max Act: 9.2871. Min Act: -0.1700
Data Index: 4661915 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2871. Min Range: -9.2871
Max Act: 9.1621. Min Act: -0.1700
Data Index: 7301088 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.8496. Min Act: -0.1700
Data Index: 5787681 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.8496. Min Act: -0.1700
Data Index: 755286 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.7871. Min Act: -0.1700
Data Index: 4661913 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.7246. Min Act: -0.1700
Data Index: 205790 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.7246. Min Act: -0.1700
Data Index: 617176 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.7246. Min Act: -0.1700
Data Index: 2751602 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.6621. Min Act: -0.1700
Data Index: 5720627 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.5996. Min Act: -0.1700
Data Index: 8770988 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.7246. Min Act: -0.1700
Data Index: 4618628 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.6621. Min Act: -0.1700
Data Index: 7201040 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.6621. Min Act: -0.1700
Data Index: 8689773 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.6621. Min Act: -0.1700
Data Index: 6766346 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.7246. Min Act: -0.1700
Data Index: 1428694 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.6621. Min Act: -0.1700
Data Index: 2025435 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.5996. Min Act: -0.1700
Data Index: 7221940 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.5996. Min Act: -0.1700
Data Index: 5075398 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.5996. Min Act: -0.1700
Data Index: 245170 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2871. Min Range: -9.2871
Max Act: 8.5996. Min Act: -0.1700
Data Index: 457286 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19