Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2825 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2680. Min Range: -6.2680
Max Act: 6.2680. Min Act: -0.1700
Data Index: 12642 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2680. Min Range: -6.2680
Max Act: 6.2055. Min Act: -0.1700
Data Index: 4350028 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2680. Min Range: -6.2680
Max Act: 6.1743. Min Act: -0.1700
Data Index: 5979696 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2680. Min Range: -6.2680
Max Act: 6.1118. Min Act: -0.1700
Data Index: 8015901 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2680. Min Range: -6.2680
Max Act: 6.1430. Min Act: -0.1700
Data Index: 4661632 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2680. Min Range: -6.2680
Max Act: 6.1430. Min Act: -0.1700
Data Index: 6267693 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2680. Min Range: -6.2680
Max Act: 6.1118. Min Act: -0.1700
Data Index: 7926796 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2680. Min Range: -6.2680
Max Act: 5.9243. Min Act: -0.1700
Data Index: 1796701 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2680. Min Range: -6.2680
Max Act: 5.9555. Min Act: -0.1700
Data Index: 2190290 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2680. Min Range: -6.2680
Max Act: 5.9243. Min Act: -0.1700
Data Index: 8333611 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2680. Min Range: -6.2680
Max Act: 5.8930. Min Act: -0.1700
Data Index: 7299161 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2680. Min Range: -6.2680
Max Act: 5.8618. Min Act: -0.1700
Data Index: 5076259 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2680. Min Range: -6.2680
Max Act: 5.8930. Min Act: -0.1700
Data Index: 5622700 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2680. Min Range: -6.2680
Max Act: 5.8305. Min Act: -0.1700
Data Index: 5508287 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2680. Min Range: -6.2680
Max Act: 5.8305. Min Act: -0.1700
Data Index: 6154109 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2680. Min Range: -6.2680
Max Act: 5.8305. Min Act: -0.1700
Data Index: 2778897 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2680. Min Range: -6.2680
Max Act: 5.8305. Min Act: -0.1700
Data Index: 914164 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2680. Min Range: -6.2680
Max Act: 5.7993. Min Act: -0.1700
Data Index: 6416533 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2680. Min Range: -6.2680
Max Act: 5.7993. Min Act: -0.1700
Data Index: 103661 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2680. Min Range: -6.2680
Max Act: 5.8305. Min Act: -0.1700
Data Index: 6496370 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19