Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1748 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.8112. Min Act: -0.1700
Data Index: 6677555 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.4674. Min Act: -0.1700
Data Index: 140012 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.4362. Min Act: -0.1700
Data Index: 5972718 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.4362. Min Act: -0.1700
Data Index: 1795168 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.3424. Min Act: -0.1700
Data Index: 4219471 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.3112. Min Act: -0.1700
Data Index: 2086931 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.2799. Min Act: -0.1700
Data Index: 8610043 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.2799. Min Act: -0.1700
Data Index: 8037730 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.2487. Min Act: -0.1700
Data Index: 6028500 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.2174. Min Act: -0.1700
Data Index: 1311930 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.2174. Min Act: -0.1700
Data Index: 2725562 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.1862. Min Act: -0.1700
Data Index: 587976 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.1862. Min Act: -0.1700
Data Index: 6435371 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.1549. Min Act: -0.1700
Data Index: 3047668 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.1549. Min Act: -0.1700
Data Index: 7029019 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.1549. Min Act: -0.1700
Data Index: 4413882 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.1237. Min Act: -0.1700
Data Index: 2613103 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.0924. Min Act: -0.1700
Data Index: 1234483 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.0612. Min Act: -0.1700
Data Index: 5192033 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8112. Min Range: -5.8112
Max Act: 5.0612. Min Act: -0.1700
Data Index: 101019 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19