Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.8754. Min Act: -0.1700
Data Index: 6520811 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.6567. Min Act: -0.1700
Data Index: 6292459 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.6254. Min Act: -0.1700
Data Index: 7898856 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.6254. Min Act: -0.1700
Data Index: 6429853 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.5629. Min Act: -0.1700
Data Index: 4871857 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.4692. Min Act: -0.1700
Data Index: 901227 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.4692. Min Act: -0.1700
Data Index: 1696980 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.4692. Min Act: -0.1700
Data Index: 6514293 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.4379. Min Act: -0.1700
Data Index: 5883813 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.3754. Min Act: -0.1700
Data Index: 8133730 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.3129. Min Act: -0.1700
Data Index: 8805605 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.3129. Min Act: -0.1700
Data Index: 6566710 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.3129. Min Act: -0.1700
Data Index: 5874257 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.3129. Min Act: -0.1700
Data Index: 7958535 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.3442. Min Act: -0.1700
Data Index: 5076124 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.2817. Min Act: -0.1700
Data Index: 3384930 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.2817. Min Act: -0.1700
Data Index: 2429446 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.2817. Min Act: -0.1700
Data Index: 4333752 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.2817. Min Act: -0.1700
Data Index: 6051339 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8754. Min Range: -5.8754
Max Act: 5.2504. Min Act: -0.1700
Data Index: 7061848 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19