Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5214 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3283. Min Range: -6.3283
Max Act: 6.3283. Min Act: -0.1700
Data Index: 5071553 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3283. Min Range: -6.3283
Max Act: 6.0471. Min Act: -0.1700
Data Index: 7048660 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.9846. Min Act: -0.1700
Data Index: 115994 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.9846. Min Act: -0.1700
Data Index: 2051651 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.9221. Min Act: -0.1700
Data Index: 6287376 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.7971. Min Act: -0.1700
Data Index: 2248921 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.8283. Min Act: -0.1700
Data Index: 3330536 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.7971. Min Act: -0.1700
Data Index: 8626369 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.7971. Min Act: -0.1700
Data Index: 4521620 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.7346. Min Act: -0.1700
Data Index: 4049264 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.7033. Min Act: -0.1700
Data Index: 2332250 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.6721. Min Act: -0.1700
Data Index: 4389851 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.6721. Min Act: -0.1700
Data Index: 2950831 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.6721. Min Act: -0.1700
Data Index: 5372103 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.6721. Min Act: -0.1700
Data Index: 777861 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.6408. Min Act: -0.1700
Data Index: 4210195 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.6408. Min Act: -0.1700
Data Index: 2084524 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.6408. Min Act: -0.1700
Data Index: 443879 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.6096. Min Act: -0.1700
Data Index: 2696859 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3283. Min Range: -6.3283
Max Act: 5.5783. Min Act: -0.1700
Data Index: 2936630 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19