Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5856 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.8241. Min Act: -0.1700
Data Index: 4026647 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.6366. Min Act: -0.1700
Data Index: 2530024 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.4178. Min Act: -0.1700
Data Index: 7286414 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.4178. Min Act: -0.1700
Data Index: 3098331 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.4491. Min Act: -0.1700
Data Index: 8610331 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.4491. Min Act: -0.1700
Data Index: 5070295 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.3241. Min Act: -0.1700
Data Index: 8721044 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.2303. Min Act: -0.1700
Data Index: 7037753 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.2303. Min Act: -0.1700
Data Index: 7111650 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.1991. Min Act: -0.1700
Data Index: 3389131 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.1678. Min Act: -0.1700
Data Index: 5220079 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.1991. Min Act: -0.1700
Data Index: 2731313 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.1366. Min Act: -0.1700
Data Index: 1690831 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.1366. Min Act: -0.1700
Data Index: 873672 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.1053. Min Act: -0.1700
Data Index: 899413 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.0741. Min Act: -0.1700
Data Index: 4841439 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.0741. Min Act: -0.1700
Data Index: 2794350 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.0116. Min Act: -0.1700
Data Index: 5806663 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.0428. Min Act: -0.1700
Data Index: 5906747 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8241. Min Range: -7.8241
Max Act: 7.0428. Min Act: -0.1700
Data Index: 3276634 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19