Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4368 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.9495. Min Act: -0.1700
Data Index: 2093400 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.8245. Min Act: -0.1700
Data Index: 1239747 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.7776. Min Act: -0.1700
Data Index: 4224892 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.7776. Min Act: -0.1700
Data Index: 165897 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.7619. Min Act: -0.1700
Data Index: 713311 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.7306. Min Act: -0.1700
Data Index: 3229798 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.7150. Min Act: -0.1700
Data Index: 5984523 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.6368. Min Act: -0.1700
Data Index: 6982604 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.6368. Min Act: -0.1700
Data Index: 7871983 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.6368. Min Act: -0.1700
Data Index: 3239223 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.6368. Min Act: -0.1700
Data Index: 5558113 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.6055. Min Act: -0.1700
Data Index: 619606 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.6055. Min Act: -0.1700
Data Index: 8595268 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.5742. Min Act: -0.1700
Data Index: 5567849 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.5898. Min Act: -0.1700
Data Index: 6801136 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.5898. Min Act: -0.1700
Data Index: 3681410 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.5742. Min Act: -0.1700
Data Index: 271879 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.5272. Min Act: -0.1700
Data Index: 2738683 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.5272. Min Act: -0.1700
Data Index: 4064138 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9495. Min Range: -3.9495
Max Act: 3.5272. Min Act: -0.1700
Data Index: 8653747 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19