Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4849 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.5614. Min Act: -0.1700
Data Index: 1891790 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.5301. Min Act: -0.1700
Data Index: 755345 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.4676. Min Act: -0.1700
Data Index: 5536158 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.4676. Min Act: -0.1700
Data Index: 8410343 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.4051. Min Act: -0.1700
Data Index: 2981425 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.4051. Min Act: -0.1700
Data Index: 7314169 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3426. Min Act: -0.1700
Data Index: 2649919 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3739. Min Act: -0.1700
Data Index: 6725197 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3114. Min Act: -0.1700
Data Index: 8194604 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3114. Min Act: -0.1700
Data Index: 8052413 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.2489. Min Act: -0.1700
Data Index: 4001559 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.2489. Min Act: -0.1700
Data Index: 3185869 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.2489. Min Act: -0.1700
Data Index: 6637227 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.2489. Min Act: -0.1700
Data Index: 1680223 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.2176. Min Act: -0.1700
Data Index: 1742334 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.2489. Min Act: -0.1700
Data Index: 4554864 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.1864. Min Act: -0.1700
Data Index: 3490400 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.1864. Min Act: -0.1700
Data Index: 6441817 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.1864. Min Act: -0.1700
Data Index: 3639641 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.1864. Min Act: -0.1700
Data Index: 5642481 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19