Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3040 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2954. Min Range: -5.2954
Max Act: 5.2954. Min Act: -0.1700
Data Index: 1818718 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2954. Min Range: -5.2954
Max Act: 5.2641. Min Act: -0.1700
Data Index: 8659308 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2954. Min Range: -5.2954
Max Act: 5.2329. Min Act: -0.1700
Data Index: 58824 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2954. Min Range: -5.2954
Max Act: 5.2016. Min Act: -0.1700
Data Index: 4137443 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2954. Min Range: -5.2954
Max Act: 5.1704. Min Act: -0.1700
Data Index: 872024 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2954. Min Range: -5.2954
Max Act: 5.1079. Min Act: -0.1700
Data Index: 5639377 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2954. Min Range: -5.2954
Max Act: 5.0766. Min Act: -0.1700
Data Index: 2984398 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2954. Min Range: -5.2954
Max Act: 5.0454. Min Act: -0.1700
Data Index: 827863 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2954. Min Range: -5.2954
Max Act: 5.0454. Min Act: -0.1700
Data Index: 7267040 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2954. Min Range: -5.2954
Max Act: 5.0454. Min Act: -0.1700
Data Index: 2640966 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2954. Min Range: -5.2954
Max Act: 5.0141. Min Act: -0.1700
Data Index: 7684735 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2954. Min Range: -5.2954
Max Act: 5.0141. Min Act: -0.1700
Data Index: 4408654 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2954. Min Range: -5.2954
Max Act: 4.9829. Min Act: -0.1700
Data Index: 655880 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2954. Min Range: -5.2954
Max Act: 4.9829. Min Act: -0.1700
Data Index: 7980054 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2954. Min Range: -5.2954
Max Act: 4.9829. Min Act: -0.1700
Data Index: 2108418 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2954. Min Range: -5.2954
Max Act: 4.9829. Min Act: -0.1700
Data Index: 5679150 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2954. Min Range: -5.2954
Max Act: 4.9516. Min Act: -0.1700
Data Index: 2247830 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2954. Min Range: -5.2954
Max Act: 4.9516. Min Act: -0.1700
Data Index: 8235964 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2954. Min Range: -5.2954
Max Act: 4.9516. Min Act: -0.1700
Data Index: 3058085 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2954. Min Range: -5.2954
Max Act: 4.9516. Min Act: -0.1700
Data Index: 2219591 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19