Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2699 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5906. Min Range: -4.5906
Max Act: 4.5906. Min Act: -0.1700
Data Index: 1307479 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5906. Min Range: -4.5906
Max Act: 4.0593. Min Act: -0.1700
Data Index: 3552610 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5906. Min Range: -4.5906
Max Act: 4.0280. Min Act: -0.1700
Data Index: 3853491 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.9811. Min Act: -0.1700
Data Index: 8455814 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.8873. Min Act: -0.1700
Data Index: 127941 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.8873. Min Act: -0.1700
Data Index: 5663897 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.8248. Min Act: -0.1700
Data Index: 1179736 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.8092. Min Act: -0.1700
Data Index: 1688116 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.8248. Min Act: -0.1700
Data Index: 2298158 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.7779. Min Act: -0.1700
Data Index: 2098731 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.7466. Min Act: -0.1700
Data Index: 5137693 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.7466. Min Act: -0.1700
Data Index: 8574068 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.7623. Min Act: -0.1700
Data Index: 8786463 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.6997. Min Act: -0.1700
Data Index: 3790785 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.7153. Min Act: -0.1700
Data Index: 5137686 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.6997. Min Act: -0.1700
Data Index: 1712373 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.6997. Min Act: -0.1700
Data Index: 7488789 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.6840. Min Act: -0.1700
Data Index: 5288367 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.6840. Min Act: -0.1700
Data Index: 3363413 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5906. Min Range: -4.5906
Max Act: 3.6684. Min Act: -0.1700
Data Index: 5137689 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19