Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2057 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.1318. Min Act: -0.1700
Data Index: 1691057 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.1318. Min Act: -0.1700
Data Index: 322830 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.1318. Min Act: -0.1700
Data Index: 6343073 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.1318. Min Act: -0.1699
Data Index: 5435553 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.1318. Min Act: -0.1700
Data Index: 6594135 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.1006. Min Act: -0.1700
Data Index: 1572732 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.1006. Min Act: -0.1700
Data Index: 7808123 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0381. Min Act: -0.1700
Data Index: 6397385 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0693. Min Act: -0.1700
Data Index: 4041462 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0693. Min Act: -0.1700
Data Index: 3051793 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0381. Min Act: -0.1700
Data Index: 4467584 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0381. Min Act: -0.1700
Data Index: 3859358 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0381. Min Act: -0.1700
Data Index: 5578957 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0381. Min Act: -0.1700
Data Index: 671326 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0068. Min Act: -0.1699
Data Index: 8576850 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0068. Min Act: -0.1700
Data Index: 1173832 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0068. Min Act: -0.1700
Data Index: 4716444 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1318. Min Range: -5.1318
Max Act: 5.0068. Min Act: -0.1700
Data Index: 4097125 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.9756. Min Act: -0.1700
Data Index: 808908 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1318. Min Range: -5.1318
Max Act: 4.9756. Min Act: -0.1700
Data Index: 774890 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19