Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5219 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.7768. Min Act: -0.1700
Data Index: 4869265 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.6206. Min Act: -0.1700
Data Index: 1492565 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.5581. Min Act: -0.1700
Data Index: 2174118 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.4331. Min Act: -0.1700
Data Index: 8116160 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.3393. Min Act: -0.1700
Data Index: 4540831 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.3393. Min Act: -0.1700
Data Index: 3173198 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.2768. Min Act: -0.1700
Data Index: 6762226 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.2456. Min Act: -0.1700
Data Index: 2407123 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.2143. Min Act: -0.1700
Data Index: 2042510 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.2143. Min Act: -0.1700
Data Index: 679459 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.1831. Min Act: -0.1700
Data Index: 3609995 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.1206. Min Act: -0.1700
Data Index: 3668803 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.1206. Min Act: -0.1700
Data Index: 4180590 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.1206. Min Act: -0.1700
Data Index: 4637955 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.0893. Min Act: -0.1700
Data Index: 2699335 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.0893. Min Act: -0.1700
Data Index: 4656013 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.0581. Min Act: -0.1700
Data Index: 4957610 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.0581. Min Act: -0.1700
Data Index: 293126 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.0893. Min Act: -0.1700
Data Index: 3438422 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7768. Min Range: -7.7768
Max Act: 7.0581. Min Act: -0.1700
Data Index: 3875096 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19