Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.6276. Min Act: -0.1700
Data Index: 1094367 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.6276. Min Act: -0.1700
Data Index: 616138 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.4401. Min Act: -0.1700
Data Index: 6174914 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.4401. Min Act: -0.1700
Data Index: 4188341 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.3151. Min Act: -0.1700
Data Index: 6338677 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.3151. Min Act: -0.1700
Data Index: 1321317 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.3151. Min Act: -0.1700
Data Index: 4396562 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.2526. Min Act: -0.1700
Data Index: 1147379 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.2526. Min Act: -0.1700
Data Index: 8044696 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.1901. Min Act: -0.1700
Data Index: 5737555 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.1276. Min Act: -0.1700
Data Index: 3938369 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.1276. Min Act: -0.1700
Data Index: 2050001 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.1276. Min Act: -0.1700
Data Index: 7086117 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.0651. Min Act: -0.1700
Data Index: 8738641 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.0026. Min Act: -0.1700
Data Index: 2361901 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.0026. Min Act: -0.1700
Data Index: 7358056 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.0026. Min Act: -0.1700
Data Index: 4627641 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.0026. Min Act: -0.1700
Data Index: 466034 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6276. Min Range: -8.6276
Max Act: 8.0026. Min Act: -0.1700
Data Index: 1273197 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6276. Min Range: -8.6276
Max Act: 7.9401. Min Act: -0.1700
Data Index: 1258937 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19