Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3480 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.7009. Min Act: -0.1700
Data Index: 250161 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.7009. Min Act: -0.1700
Data Index: 7795905 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.6384. Min Act: -0.1700
Data Index: 2789089 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.4509. Min Act: -0.1700
Data Index: 8430100 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.4509. Min Act: -0.1700
Data Index: 7894473 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.4196. Min Act: -0.1700
Data Index: 5039347 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.4196. Min Act: -0.1700
Data Index: 8052149 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.4196. Min Act: -0.1700
Data Index: 6328819 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.3571. Min Act: -0.1700
Data Index: 4197200 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.3884. Min Act: -0.1700
Data Index: 1016237 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.3884. Min Act: -0.1700
Data Index: 6078843 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.3259. Min Act: -0.1700
Data Index: 4956707 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.3571. Min Act: -0.1700
Data Index: 695719 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.3571. Min Act: -0.1700
Data Index: 5734139 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.3571. Min Act: -0.1700
Data Index: 299873 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.3571. Min Act: -0.1700
Data Index: 4211955 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.3259. Min Act: -0.1700
Data Index: 607032 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.3259. Min Act: -0.1700
Data Index: 8036925 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.2946. Min Act: -0.1700
Data Index: 5488730 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7009. Min Range: -4.7009
Max Act: 4.3259. Min Act: -0.1700
Data Index: 4725606 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19