Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1564 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.6377. Min Act: -0.1700
Data Index: 2857499 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.5438. Min Act: -0.1700
Data Index: 2333824 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.5125. Min Act: -0.1700
Data Index: 5809621 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.5125. Min Act: -0.1700
Data Index: 7599102 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.4968. Min Act: -0.1700
Data Index: 6879646 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.5125. Min Act: -0.1700
Data Index: 2512545 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.4812. Min Act: -0.1700
Data Index: 4426634 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.4812. Min Act: -0.1700
Data Index: 3922129 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.4342. Min Act: -0.1700
Data Index: 8701131 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.4342. Min Act: -0.1700
Data Index: 3922126 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.4342. Min Act: -0.1700
Data Index: 7578999 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.4185. Min Act: -0.1700
Data Index: 198119 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.4028. Min Act: -0.1700
Data Index: 570819 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.3871. Min Act: -0.1700
Data Index: 2128802 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.3871. Min Act: -0.1700
Data Index: 1997736 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.4028. Min Act: -0.1700
Data Index: 5570473 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.4028. Min Act: -0.1700
Data Index: 4426633 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.3871. Min Act: -0.1700
Data Index: 2197781 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.3715. Min Act: -0.1700
Data Index: 191333 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6377. Min Range: -3.6377
Max Act: 3.3715. Min Act: -0.1700
Data Index: 5365248 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19