Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3878 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.2162. Min Act: -0.1700
Data Index: 8627228 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.1850. Min Act: -0.1700
Data Index: 4323470 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.1225. Min Act: -0.1700
Data Index: 6483732 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.1225. Min Act: -0.1700
Data Index: 6759538 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.1537. Min Act: -0.1700
Data Index: 2939113 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.0912. Min Act: -0.1700
Data Index: 1214334 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.0912. Min Act: -0.1700
Data Index: 1214333 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.0600. Min Act: -0.1700
Data Index: 1613345 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.0600. Min Act: -0.1700
Data Index: 7873823 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.0600. Min Act: -0.1700
Data Index: 4100609 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.0912. Min Act: -0.1700
Data Index: 5241952 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.0600. Min Act: -0.1700
Data Index: 490978 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2162. Min Range: -5.2162
Max Act: 4.9975. Min Act: -0.1700
Data Index: 6895892 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.0287. Min Act: -0.1700
Data Index: 8389956 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.0287. Min Act: -0.1700
Data Index: 5003647 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.0287. Min Act: -0.1700
Data Index: 6794477 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.0287. Min Act: -0.1700
Data Index: 4645922 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.0287. Min Act: -0.1700
Data Index: 3206255 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.0287. Min Act: -0.1700
Data Index: 8627226 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2162. Min Range: -5.2162
Max Act: 5.0287. Min Act: -0.1700
Data Index: 2760339 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19