Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2095 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.3562. Min Act: -0.1700
Data Index: 485745 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.1999. Min Act: -0.1700
Data Index: 4272254 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.1374. Min Act: -0.1700
Data Index: 7681384 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.1374. Min Act: -0.1700
Data Index: 5033955 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.0749. Min Act: -0.1700
Data Index: 3092522 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.0749. Min Act: -0.1700
Data Index: 6373526 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.0749. Min Act: -0.1700
Data Index: 5441855 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.0437. Min Act: -0.1700
Data Index: 7700845 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3562. Min Range: -6.3562
Max Act: 6.0437. Min Act: -0.1700
Data Index: 3106513 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3562. Min Range: -6.3562
Max Act: 5.9812. Min Act: -0.1700
Data Index: 4074878 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3562. Min Range: -6.3562
Max Act: 5.9812. Min Act: -0.1700
Data Index: 7525582 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3562. Min Range: -6.3562
Max Act: 5.9499. Min Act: -0.1700
Data Index: 1306267 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3562. Min Range: -6.3562
Max Act: 5.9812. Min Act: -0.1700
Data Index: 4701716 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3562. Min Range: -6.3562
Max Act: 5.9187. Min Act: -0.1700
Data Index: 7779913 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3562. Min Range: -6.3562
Max Act: 5.8249. Min Act: -0.1700
Data Index: 5697683 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3562. Min Range: -6.3562
Max Act: 5.7937. Min Act: -0.1700
Data Index: 4335025 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3562. Min Range: -6.3562
Max Act: 5.7937. Min Act: -0.1700
Data Index: 6603465 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3562. Min Range: -6.3562
Max Act: 5.7624. Min Act: -0.1700
Data Index: 4783946 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3562. Min Range: -6.3562
Max Act: 5.7312. Min Act: -0.1700
Data Index: 1454940 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3562. Min Range: -6.3562
Max Act: 5.7312. Min Act: -0.1700
Data Index: 7568279 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19