Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 304 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3594. Min Range: -5.3594
Max Act: 5.3594. Min Act: -0.1700
Data Index: 1869263 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3594. Min Range: -5.3594
Max Act: 5.2031. Min Act: -0.1700
Data Index: 5882287 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3594. Min Range: -5.3594
Max Act: 5.1719. Min Act: -0.1700
Data Index: 1961737 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3594. Min Range: -5.3594
Max Act: 5.0781. Min Act: -0.1700
Data Index: 2332538 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.9219. Min Act: -0.1700
Data Index: 8291878 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.9531. Min Act: -0.1700
Data Index: 3152031 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.9219. Min Act: -0.1700
Data Index: 4436444 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.9219. Min Act: -0.1700
Data Index: 4576964 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.9219. Min Act: -0.1700
Data Index: 1479745 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.9219. Min Act: -0.1700
Data Index: 2498123 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.8594. Min Act: -0.1700
Data Index: 8597073 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.8594. Min Act: -0.1700
Data Index: 1794246 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.8594. Min Act: -0.1700
Data Index: 1209977 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.8281. Min Act: -0.1700
Data Index: 8005240 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.8281. Min Act: -0.1700
Data Index: 7093164 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.7969. Min Act: -0.1700
Data Index: 5990190 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.7969. Min Act: -0.1700
Data Index: 6348855 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.7656. Min Act: -0.1700
Data Index: 3621794 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.7969. Min Act: -0.1700
Data Index: 1546838 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3594. Min Range: -5.3594
Max Act: 4.7969. Min Act: -0.1700
Data Index: 4062878 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19