Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4450 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.9971. Min Act: -0.1700
Data Index: 241487 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.9971. Min Act: -0.1700
Data Index: 6977367 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.9658. Min Act: -0.1700
Data Index: 4589881 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.9658. Min Act: -0.1700
Data Index: 348804 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.9658. Min Act: -0.1700
Data Index: 7523423 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.9033. Min Act: -0.1700
Data Index: 4081181 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.8721. Min Act: -0.1700
Data Index: 2184620 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.8721. Min Act: -0.1700
Data Index: 6162795 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.8096. Min Act: -0.1700
Data Index: 7682602 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.8096. Min Act: -0.1700
Data Index: 3167023 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.8096. Min Act: -0.1700
Data Index: 5701877 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.7783. Min Act: -0.1700
Data Index: 6957932 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.7783. Min Act: -0.1700
Data Index: 3476055 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.7783. Min Act: -0.1700
Data Index: 1722073 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.7783. Min Act: -0.1700
Data Index: 2167214 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.7471. Min Act: -0.1700
Data Index: 5355169 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.7471. Min Act: -0.1700
Data Index: 4778484 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.7783. Min Act: -0.1700
Data Index: 1222893 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.7158. Min Act: -0.1700
Data Index: 4033879 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9971. Min Range: -5.9971
Max Act: 5.7158. Min Act: -0.1700
Data Index: 1052964 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19