Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1764 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.8756. Min Act: -0.1700
Data Index: 5075561 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.7194. Min Act: -0.1700
Data Index: 5495022 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.5944. Min Act: -0.1700
Data Index: 5495026 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.5319. Min Act: -0.1700
Data Index: 2610765 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.5631. Min Act: -0.1700
Data Index: 2927069 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.5319. Min Act: -0.1700
Data Index: 6210227 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.4381. Min Act: -0.1700
Data Index: 2071186 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.4069. Min Act: -0.1700
Data Index: 1293004 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.4381. Min Act: -0.1700
Data Index: 4480629 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.4381. Min Act: -0.1700
Data Index: 2927067 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.4069. Min Act: -0.1700
Data Index: 5659937 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.3756. Min Act: -0.1700
Data Index: 4683771 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.3756. Min Act: -0.1700
Data Index: 4132522 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.3756. Min Act: -0.1700
Data Index: 7306804 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.3444. Min Act: -0.1700
Data Index: 5296486 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.3756. Min Act: -0.1700
Data Index: 2869295 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.4069. Min Act: -0.1700
Data Index: 3281805 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.3756. Min Act: -0.1700
Data Index: 2622640 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.3444. Min Act: -0.1700
Data Index: 2118750 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8756. Min Range: -5.8756
Max Act: 5.3131. Min Act: -0.1700
Data Index: 4311795 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19