Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3641 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7944. Min Range: -7.7944
Max Act: 7.7944. Min Act: -0.1700
Data Index: 2212927 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7944. Min Range: -7.7944
Max Act: 7.6381. Min Act: -0.1700
Data Index: 6072843 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7944. Min Range: -7.7944
Max Act: 7.2631. Min Act: -0.1700
Data Index: 900448 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7944. Min Range: -7.7944
Max Act: 7.2319. Min Act: -0.1700
Data Index: 4585598 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7944. Min Range: -7.7944
Max Act: 7.1069. Min Act: -0.1700
Data Index: 2806886 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7944. Min Range: -7.7944
Max Act: 7.0444. Min Act: -0.1700
Data Index: 19439 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7944. Min Range: -7.7944
Max Act: 7.0444. Min Act: -0.1700
Data Index: 2925269 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7944. Min Range: -7.7944
Max Act: 7.0131. Min Act: -0.1700
Data Index: 6928269 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7944. Min Range: -7.7944
Max Act: 7.0131. Min Act: -0.1700
Data Index: 7214277 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7944. Min Range: -7.7944
Max Act: 6.9506. Min Act: -0.1700
Data Index: 5030827 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7944. Min Range: -7.7944
Max Act: 6.9194. Min Act: -0.1700
Data Index: 5756794 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7944. Min Range: -7.7944
Max Act: 6.8569. Min Act: -0.1700
Data Index: 1787648 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7944. Min Range: -7.7944
Max Act: 6.8881. Min Act: -0.1700
Data Index: 7002895 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7944. Min Range: -7.7944
Max Act: 6.9194. Min Act: -0.1700
Data Index: 7551139 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7944. Min Range: -7.7944
Max Act: 6.8881. Min Act: -0.1700
Data Index: 7859695 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7944. Min Range: -7.7944
Max Act: 6.8256. Min Act: -0.1700
Data Index: 3339183 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7944. Min Range: -7.7944
Max Act: 6.8569. Min Act: -0.1700
Data Index: 5379628 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7944. Min Range: -7.7944
Max Act: 6.8569. Min Act: -0.1700
Data Index: 5909250 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7944. Min Range: -7.7944
Max Act: 6.8256. Min Act: -0.1700
Data Index: 6072834 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7944. Min Range: -7.7944
Max Act: 6.7944. Min Act: -0.1700
Data Index: 2661027 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19