Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3379 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.7880. Min Act: -0.1700
Data Index: 1247169 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.5068. Min Act: -0.1700
Data Index: 4484988 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.4443. Min Act: -0.1700
Data Index: 6570051 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.4130. Min Act: -0.1700
Data Index: 6234866 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.3505. Min Act: -0.1700
Data Index: 8201537 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.3505. Min Act: -0.1700
Data Index: 1102054 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.2568. Min Act: -0.1700
Data Index: 1381494 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.2568. Min Act: -0.1700
Data Index: 2469019 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.2568. Min Act: -0.1700
Data Index: 2193888 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.2568. Min Act: -0.1700
Data Index: 5241642 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.2255. Min Act: -0.1700
Data Index: 1226789 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.2255. Min Act: -0.1700
Data Index: 6720035 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.1943. Min Act: -0.1700
Data Index: 7755879 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.1630. Min Act: -0.1700
Data Index: 4581449 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.1630. Min Act: -0.1700
Data Index: 1841837 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.1318. Min Act: -0.1700
Data Index: 1440462 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.1005. Min Act: -0.1700
Data Index: 5487036 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.1005. Min Act: -0.1700
Data Index: 5594198 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.1005. Min Act: -0.1700
Data Index: 7476237 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7880. Min Range: -6.7880
Max Act: 6.1005. Min Act: -0.1700
Data Index: 5643721 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19