Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3796 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3358. Min Range: -4.3358
Max Act: 4.3358. Min Act: -0.1700
Data Index: 2999271 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3358. Min Range: -4.3358
Max Act: 4.2733. Min Act: -0.1700
Data Index: 6345583 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3358. Min Range: -4.3358
Max Act: 4.0858. Min Act: -0.1700
Data Index: 2832965 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3358. Min Range: -4.3358
Max Act: 4.0858. Min Act: -0.1700
Data Index: 6434596 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.9920. Min Act: -0.1700
Data Index: 5251591 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.9920. Min Act: -0.1700
Data Index: 1854426 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.9607. Min Act: -0.1700
Data Index: 8509737 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.9295. Min Act: -0.1700
Data Index: 7275193 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.9295. Min Act: -0.1700
Data Index: 6956345 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.9295. Min Act: -0.1700
Data Index: 6723795 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.9295. Min Act: -0.1700
Data Index: 2354317 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.9295. Min Act: -0.1700
Data Index: 1091264 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.8982. Min Act: -0.1700
Data Index: 6662874 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.8982. Min Act: -0.1700
Data Index: 53641 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.8982. Min Act: -0.1700
Data Index: 2202867 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.9295. Min Act: -0.1700
Data Index: 4659556 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.8982. Min Act: -0.1700
Data Index: 1492649 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.8982. Min Act: -0.1700
Data Index: 4240320 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.8669. Min Act: -0.1700
Data Index: 7011268 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3358. Min Range: -4.3358
Max Act: 3.8669. Min Act: -0.1700
Data Index: 7179475 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19