Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2753 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.8855. Min Act: -0.1700
Data Index: 6096963 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.7605. Min Act: -0.1700
Data Index: 1906991 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6980. Min Act: -0.1700
Data Index: 4412557 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6980. Min Act: -0.1700
Data Index: 7636845 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6668. Min Act: -0.1700
Data Index: 6170989 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6668. Min Act: -0.1700
Data Index: 7122700 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6668. Min Act: -0.1700
Data Index: 2334837 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6668. Min Act: -0.1700
Data Index: 1449818 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6355. Min Act: -0.1700
Data Index: 5375026 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6355. Min Act: -0.1700
Data Index: 877639 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6355. Min Act: -0.1700
Data Index: 3626651 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6355. Min Act: -0.1700
Data Index: 3455061 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6043. Min Act: -0.1700
Data Index: 7238857 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6355. Min Act: -0.1700
Data Index: 3551041 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6668. Min Act: -0.1700
Data Index: 4839500 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6043. Min Act: -0.1700
Data Index: 2271429 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6043. Min Act: -0.1700
Data Index: 5296025 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6043. Min Act: -0.1700
Data Index: 392673 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.5730. Min Act: -0.1700
Data Index: 5380612 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6043. Min Act: -0.1700
Data Index: 5399591 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19