Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1279 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.9409. Min Act: -0.1700
Data Index: 1949395 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.8783. Min Act: -0.1700
Data Index: 8019511 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.7845. Min Act: -0.1700
Data Index: 4729823 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.7845. Min Act: -0.1700
Data Index: 1429045 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.7689. Min Act: -0.1700
Data Index: 7613262 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.7532. Min Act: -0.1700
Data Index: 7953241 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.6907. Min Act: -0.1700
Data Index: 6871643 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.6907. Min Act: -0.1700
Data Index: 343395 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.6907. Min Act: -0.1700
Data Index: 7830236 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.6594. Min Act: -0.1700
Data Index: 8262054 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.6594. Min Act: -0.1700
Data Index: 4001740 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.6281. Min Act: -0.1700
Data Index: 8366092 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.6281. Min Act: -0.1700
Data Index: 7143623 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.6124. Min Act: -0.1700
Data Index: 5022493 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.6281. Min Act: -0.1700
Data Index: 5259096 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.5968. Min Act: -0.1700
Data Index: 1424029 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.5811. Min Act: -0.1700
Data Index: 3880007 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.5811. Min Act: -0.1700
Data Index: 1734145 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.5811. Min Act: -0.1700
Data Index: 7348404 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9409. Min Range: -3.9409
Max Act: 3.5811. Min Act: -0.1700
Data Index: 5570161 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19