Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4553 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3093. Min Range: -10.3093
Max Act: 10.3093. Min Act: -0.1700
Data Index: 7376304 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3093. Min Range: -10.3093
Max Act: 10.2468. Min Act: -0.1700
Data Index: 4565008 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3093. Min Range: -10.3093
Max Act: 10.2468. Min Act: -0.1700
Data Index: 1233466 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3093. Min Range: -10.3093
Max Act: 10.1218. Min Act: -0.1700
Data Index: 3752606 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3093. Min Range: -10.3093
Max Act: 9.9968. Min Act: -0.1700
Data Index: 5585037 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3093. Min Range: -10.3093
Max Act: 10.0593. Min Act: -0.1700
Data Index: 3312664 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3093. Min Range: -10.3093
Max Act: 9.9968. Min Act: -0.1700
Data Index: 8568351 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3093. Min Range: -10.3093
Max Act: 9.9343. Min Act: -0.1700
Data Index: 3590393 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3093. Min Range: -10.3093
Max Act: 9.9968. Min Act: -0.1700
Data Index: 80800 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3093. Min Range: -10.3093
Max Act: 9.8093. Min Act: -0.1700
Data Index: 2690465 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3093. Min Range: -10.3093
Max Act: 9.8718. Min Act: -0.1700
Data Index: 908205 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3093. Min Range: -10.3093
Max Act: 9.8718. Min Act: -0.1700
Data Index: 1039514 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3093. Min Range: -10.3093
Max Act: 9.8718. Min Act: -0.1700
Data Index: 519854 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3093. Min Range: -10.3093
Max Act: 9.8093. Min Act: -0.1700
Data Index: 3362547 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3093. Min Range: -10.3093
Max Act: 9.8093. Min Act: -0.1700
Data Index: 3504641 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3093. Min Range: -10.3093
Max Act: 9.7468. Min Act: -0.1700
Data Index: 4003993 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3093. Min Range: -10.3093
Max Act: 9.7468. Min Act: -0.1700
Data Index: 5050504 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3093. Min Range: -10.3093
Max Act: 9.7468. Min Act: -0.1700
Data Index: 1415471 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3093. Min Range: -10.3093
Max Act: 9.7468. Min Act: -0.1700
Data Index: 2147847 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3093. Min Range: -10.3093
Max Act: 9.7468. Min Act: -0.1700
Data Index: 1450326 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19