Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.8328. Min Act: -0.1700
Data Index: 5901976 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.8328. Min Act: -0.1700
Data Index: 3444601 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.8015. Min Act: -0.1700
Data Index: 4838710 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.7859. Min Act: -0.1700
Data Index: 7621349 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.7703. Min Act: -0.1700
Data Index: 7978830 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.7859. Min Act: -0.1700
Data Index: 2941211 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.7703. Min Act: -0.1700
Data Index: 7031690 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.7703. Min Act: -0.1700
Data Index: 3344981 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.7546. Min Act: -0.1700
Data Index: 4378007 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.7390. Min Act: -0.1700
Data Index: 7029932 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.7233. Min Act: -0.1700
Data Index: 4735923 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.7390. Min Act: -0.1700
Data Index: 6384383 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.6920. Min Act: -0.1700
Data Index: 7885895 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.7390. Min Act: -0.1700
Data Index: 6362293 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.7077. Min Act: -0.1700
Data Index: 1752037 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.6764. Min Act: -0.1700
Data Index: 1192647 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.6920. Min Act: -0.1700
Data Index: 3158846 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.6764. Min Act: -0.1700
Data Index: 2760414 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.7077. Min Act: -0.1700
Data Index: 877932 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8328. Min Range: -3.8328
Max Act: 3.6608. Min Act: -0.1700
Data Index: 7293678 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19