Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3385 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.2029. Min Act: -0.1700
Data Index: 1429107 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2029. Min Range: -8.2029
Max Act: 8.1404. Min Act: -0.1700
Data Index: 51223 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.9842. Min Act: -0.1700
Data Index: 7688495 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.9529. Min Act: -0.1700
Data Index: 5681125 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.9529. Min Act: -0.1700
Data Index: 3793628 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.9217. Min Act: -0.1700
Data Index: 1552465 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.9217. Min Act: -0.1700
Data Index: 1947254 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.8904. Min Act: -0.1700
Data Index: 3007336 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.8279. Min Act: -0.1700
Data Index: 7579054 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.7967. Min Act: -0.1700
Data Index: 5863698 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.8279. Min Act: -0.1700
Data Index: 6431925 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.7967. Min Act: -0.1700
Data Index: 7603857 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.7654. Min Act: -0.1700
Data Index: 6913455 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.7654. Min Act: -0.1700
Data Index: 1640126 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.7654. Min Act: -0.1700
Data Index: 4569157 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.7342. Min Act: -0.1700
Data Index: 5479209 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.7342. Min Act: -0.1700
Data Index: 1875553 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.6717. Min Act: -0.1700
Data Index: 4388097 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.7029. Min Act: -0.1700
Data Index: 7016593 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2029. Min Range: -8.2029
Max Act: 7.6404. Min Act: -0.1700
Data Index: 891287 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19