Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4793 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.2740. Min Act: -0.1700
Data Index: 1391923 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.1490. Min Act: -0.1700
Data Index: 8805166 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.1490. Min Act: -0.1700
Data Index: 5880875 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.1178. Min Act: -0.1700
Data Index: 5070592 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.1490. Min Act: -0.1700
Data Index: 5070574 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.1178. Min Act: -0.1700
Data Index: 7923150 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.1178. Min Act: -0.1700
Data Index: 5484709 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.1178. Min Act: -0.1700
Data Index: 4004171 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.1178. Min Act: -0.1700
Data Index: 3824959 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.0865. Min Act: -0.1700
Data Index: 3071726 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.0553. Min Act: -0.1700
Data Index: 4246781 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.0553. Min Act: -0.1700
Data Index: 4335221 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.0553. Min Act: -0.1700
Data Index: 2043082 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.0240. Min Act: -0.1700
Data Index: 1522128 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.0553. Min Act: -0.1700
Data Index: 4335203 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.0553. Min Act: -0.1700
Data Index: 4471947 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.0553. Min Act: -0.1700
Data Index: 178518 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2740. Min Range: -5.2740
Max Act: 4.9928. Min Act: -0.1699
Data Index: 4735238 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.0240. Min Act: -0.1700
Data Index: 4341549 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2740. Min Range: -5.2740
Max Act: 4.9928. Min Act: -0.1700
Data Index: 835700 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19