Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1179. Min Range: -5.1179
Max Act: 5.1179. Min Act: -0.1700
Data Index: 6362701 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.9304. Min Act: -0.1700
Data Index: 573408 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.9304. Min Act: -0.1700
Data Index: 1264471 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.8992. Min Act: -0.1700
Data Index: 5262561 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.8679. Min Act: -0.1700
Data Index: 2580262 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.8367. Min Act: -0.1700
Data Index: 807291 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.8367. Min Act: -0.1700
Data Index: 1785440 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.7742. Min Act: -0.1700
Data Index: 657320 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.7429. Min Act: -0.1700
Data Index: 1132413 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.7429. Min Act: -0.1700
Data Index: 3158733 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.7117. Min Act: -0.1700
Data Index: 600966 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.6804. Min Act: -0.1700
Data Index: 3841723 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.7117. Min Act: -0.1700
Data Index: 6272749 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.6804. Min Act: -0.1700
Data Index: 6795218 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.6492. Min Act: -0.1700
Data Index: 1512539 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.6492. Min Act: -0.1700
Data Index: 2852964 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.6492. Min Act: -0.1700
Data Index: 7984401 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.6492. Min Act: -0.1700
Data Index: 1260107 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.6179. Min Act: -0.1700
Data Index: 8222808 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1179. Min Range: -5.1179
Max Act: 4.5554. Min Act: -0.1700
Data Index: 29700 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19