Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3633 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2474. Min Range: -4.2474
Max Act: 4.2474. Min Act: -0.1700
Data Index: 4749758 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2474. Min Range: -4.2474
Max Act: 4.1536. Min Act: -0.1700
Data Index: 2263785 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2474. Min Range: -4.2474
Max Act: 4.1536. Min Act: -0.1700
Data Index: 8530527 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2474. Min Range: -4.2474
Max Act: 4.1536. Min Act: -0.1700
Data Index: 7908435 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2474. Min Range: -4.2474
Max Act: 4.0911. Min Act: -0.1700
Data Index: 8141594 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2474. Min Range: -4.2474
Max Act: 4.0599. Min Act: -0.1700
Data Index: 4127067 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2474. Min Range: -4.2474
Max Act: 3.9348. Min Act: -0.1700
Data Index: 3123290 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2474. Min Range: -4.2474
Max Act: 3.9348. Min Act: -0.1700
Data Index: 6156827 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2474. Min Range: -4.2474
Max Act: 3.9036. Min Act: -0.1700
Data Index: 171898 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2474. Min Range: -4.2474
Max Act: 3.8879. Min Act: -0.1700
Data Index: 4070046 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2474. Min Range: -4.2474
Max Act: 3.9036. Min Act: -0.1700
Data Index: 3037817 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2474. Min Range: -4.2474
Max Act: 3.8723. Min Act: -0.1700
Data Index: 1454486 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2474. Min Range: -4.2474
Max Act: 3.8879. Min Act: -0.1700
Data Index: 7361845 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2474. Min Range: -4.2474
Max Act: 3.8567. Min Act: -0.1700
Data Index: 4538632 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2474. Min Range: -4.2474
Max Act: 3.8567. Min Act: -0.1700
Data Index: 2981114 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2474. Min Range: -4.2474
Max Act: 3.8723. Min Act: -0.1700
Data Index: 2487597 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2474. Min Range: -4.2474
Max Act: 3.8567. Min Act: -0.1700
Data Index: 676828 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2474. Min Range: -4.2474
Max Act: 3.8410. Min Act: -0.1700
Data Index: 7748408 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2474. Min Range: -4.2474
Max Act: 3.8410. Min Act: -0.1700
Data Index: 6160431 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2474. Min Range: -4.2474
Max Act: 3.8410. Min Act: -0.1700
Data Index: 915009 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19