Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5409 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0986. Min Range: -9.0986
Max Act: 9.0986. Min Act: -0.1700
Data Index: 8361668 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0986. Min Range: -9.0986
Max Act: 9.0361. Min Act: -0.1700
Data Index: 6687101 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.9736. Min Act: -0.1700
Data Index: 3554254 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.9736. Min Act: -0.1700
Data Index: 3177031 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.9736. Min Act: -0.1700
Data Index: 3653223 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.8486. Min Act: -0.1700
Data Index: 6129121 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.9111. Min Act: -0.1700
Data Index: 246049 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.9111. Min Act: -0.1700
Data Index: 662233 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.8486. Min Act: -0.1700
Data Index: 1809928 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.8486. Min Act: -0.1700
Data Index: 4576715 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.8486. Min Act: -0.1700
Data Index: 4511589 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.9111. Min Act: -0.1700
Data Index: 4269617 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.7861. Min Act: -0.1700
Data Index: 4182765 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.8486. Min Act: -0.1700
Data Index: 6634573 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.8486. Min Act: -0.1700
Data Index: 282960 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.7861. Min Act: -0.1700
Data Index: 663064 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.8486. Min Act: -0.1700
Data Index: 4731300 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.7861. Min Act: -0.1700
Data Index: 4894158 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.7861. Min Act: -0.1700
Data Index: 1491557 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0986. Min Range: -9.0986
Max Act: 8.7236. Min Act: -0.1700
Data Index: 5913717 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19