Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3570 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2512. Min Range: -6.2512
Max Act: 6.2512. Min Act: -0.1700
Data Index: 2734557 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2512. Min Range: -6.2512
Max Act: 6.1887. Min Act: -0.1700
Data Index: 4047327 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2512. Min Range: -6.2512
Max Act: 6.1262. Min Act: -0.1700
Data Index: 985497 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2512. Min Range: -6.2512
Max Act: 6.0012. Min Act: -0.1700
Data Index: 7843022 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.9387. Min Act: -0.1700
Data Index: 6854929 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.9387. Min Act: -0.1700
Data Index: 8624085 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.9074. Min Act: -0.1700
Data Index: 3631817 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.9074. Min Act: -0.1700
Data Index: 7448252 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.9074. Min Act: -0.1700
Data Index: 3508509 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.8762. Min Act: -0.1700
Data Index: 5312080 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.8762. Min Act: -0.1700
Data Index: 7664756 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.8762. Min Act: -0.1700
Data Index: 4591022 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.8137. Min Act: -0.1700
Data Index: 5611800 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.8762. Min Act: -0.1700
Data Index: 3817812 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.8449. Min Act: -0.1700
Data Index: 6240855 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.8449. Min Act: -0.1700
Data Index: 3477758 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.8137. Min Act: -0.1700
Data Index: 3012104 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.8449. Min Act: -0.1700
Data Index: 8011392 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.8449. Min Act: -0.1700
Data Index: 656262 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2512. Min Range: -6.2512
Max Act: 5.8137. Min Act: -0.1700
Data Index: 4838773 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19