Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1115 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.4663. Min Act: -0.1700
Data Index: 8216031 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.4663. Min Act: -0.1700
Data Index: 906726 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.4038. Min Act: -0.1700
Data Index: 6812331 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.3726. Min Act: -0.1700
Data Index: 2383784 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.3726. Min Act: -0.1700
Data Index: 8497849 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.3726. Min Act: -0.1700
Data Index: 6588824 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.3726. Min Act: -0.1700
Data Index: 1534860 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.3726. Min Act: -0.1700
Data Index: 2683616 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.4038. Min Act: -0.1700
Data Index: 6588807 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.3413. Min Act: -0.1700
Data Index: 8777872 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.3413. Min Act: -0.1700
Data Index: 5242031 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.3413. Min Act: -0.1700
Data Index: 2816529 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.2788. Min Act: -0.1700
Data Index: 6643838 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.3101. Min Act: -0.1700
Data Index: 6553585 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.2788. Min Act: -0.1700
Data Index: 8121465 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.3101. Min Act: -0.1700
Data Index: 7207011 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.3101. Min Act: -0.1700
Data Index: 5758031 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.2788. Min Act: -0.1700
Data Index: 6940652 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.3101. Min Act: -0.1700
Data Index: 5751487 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4663. Min Range: -5.4663
Max Act: 5.3101. Min Act: -0.1700
Data Index: 4713427 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19