Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 740 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.3781. Min Act: -0.1700
Data Index: 1420636 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.4094. Min Act: -0.1700
Data Index: 3650273 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.2531. Min Act: -0.1700
Data Index: 6151395 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.2219. Min Act: -0.1700
Data Index: 3101469 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.1906. Min Act: -0.1700
Data Index: 3429776 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.2219. Min Act: -0.1700
Data Index: 3794437 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.1906. Min Act: -0.1700
Data Index: 4156564 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.1594. Min Act: -0.1700
Data Index: 4344166 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.0969. Min Act: -0.1700
Data Index: 8033302 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.0969. Min Act: -0.1700
Data Index: 1107875 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.0969. Min Act: -0.1700
Data Index: 1973746 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.0656. Min Act: -0.1700
Data Index: 8637981 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.0656. Min Act: -0.1700
Data Index: 4150303 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.0343. Min Act: -0.1700
Data Index: 836943 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.0343. Min Act: -0.1700
Data Index: 3685034 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.0343. Min Act: -0.1700
Data Index: 1604890 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4094. Min Range: -4.4094
Max Act: 4.0031. Min Act: -0.1700
Data Index: 3063974 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4094. Min Range: -4.4094
Max Act: 3.9406. Min Act: -0.1700
Data Index: 5615296 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4094. Min Range: -4.4094
Max Act: 3.9718. Min Act: -0.1700
Data Index: 7745159 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4094. Min Range: -4.4094
Max Act: 3.9718. Min Act: -0.1700
Data Index: 1129236 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19