Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4610 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.9241. Min Act: -0.1700
Data Index: 4805870 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.8929. Min Act: -0.1700
Data Index: 7768359 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.7991. Min Act: -0.1700
Data Index: 1218055 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.7366. Min Act: -0.1700
Data Index: 5605568 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.7366. Min Act: -0.1700
Data Index: 5560373 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.7366. Min Act: -0.1700
Data Index: 6593474 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.7054. Min Act: -0.1700
Data Index: 4534451 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.6741. Min Act: -0.1700
Data Index: 1599008 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.6741. Min Act: -0.1700
Data Index: 253007 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.6741. Min Act: -0.1700
Data Index: 3186495 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.5804. Min Act: -0.1700
Data Index: 4863906 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.6116. Min Act: -0.1700
Data Index: 2434064 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.5804. Min Act: -0.1700
Data Index: 1865114 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.5804. Min Act: -0.1700
Data Index: 1189726 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.6116. Min Act: -0.1700
Data Index: 5732069 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.5491. Min Act: -0.1700
Data Index: 7409220 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.5491. Min Act: -0.1700
Data Index: 1045953 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.5491. Min Act: -0.1700
Data Index: 5438253 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.5179. Min Act: -0.1700
Data Index: 2846801 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9241. Min Range: -5.9241
Max Act: 5.5179. Min Act: -0.1700
Data Index: 2846800 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19