Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6361 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.6309. Min Act: -0.1700
Data Index: 6618576 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.4747. Min Act: -0.1700
Data Index: 4465950 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.4122. Min Act: -0.1700
Data Index: 5880162 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.4122. Min Act: -0.1700
Data Index: 5158764 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.4122. Min Act: -0.1700
Data Index: 5964390 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.3809. Min Act: -0.1700
Data Index: 123681 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.3809. Min Act: -0.1700
Data Index: 4417496 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.3497. Min Act: -0.1700
Data Index: 3103545 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.3497. Min Act: -0.1700
Data Index: 3207722 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.3184. Min Act: -0.1700
Data Index: 3410246 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.3184. Min Act: -0.1700
Data Index: 7701994 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.3184. Min Act: -0.1700
Data Index: 6825472 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.2872. Min Act: -0.1700
Data Index: 1540099 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.2872. Min Act: -0.1700
Data Index: 949901 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.2872. Min Act: -0.1700
Data Index: 1540108 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.2872. Min Act: -0.1700
Data Index: 2849565 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.2872. Min Act: -0.1700
Data Index: 2634756 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.2872. Min Act: -0.1700
Data Index: 2987853 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.2872. Min Act: -0.1700
Data Index: 6044124 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6309. Min Range: -4.6309
Max Act: 4.2872. Min Act: -0.1700
Data Index: 1089607 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19