Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3946 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2264. Min Range: -8.2264
Max Act: 8.2264. Min Act: -0.1700
Data Index: 549817 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2264. Min Range: -8.2264
Max Act: 7.6639. Min Act: -0.1700
Data Index: 7624154 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2264. Min Range: -8.2264
Max Act: 7.4139. Min Act: -0.1700
Data Index: 7752738 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2264. Min Range: -8.2264
Max Act: 7.3826. Min Act: -0.1700
Data Index: 6135826 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2264. Min Range: -8.2264
Max Act: 7.3514. Min Act: -0.1700
Data Index: 1385952 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2264. Min Range: -8.2264
Max Act: 7.1326. Min Act: -0.1700
Data Index: 2789878 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2264. Min Range: -8.2264
Max Act: 7.1639. Min Act: -0.1700
Data Index: 2094533 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2264. Min Range: -8.2264
Max Act: 7.0389. Min Act: -0.1700
Data Index: 2270373 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2264. Min Range: -8.2264
Max Act: 7.0389. Min Act: -0.1700
Data Index: 3091512 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2264. Min Range: -8.2264
Max Act: 7.0076. Min Act: -0.1700
Data Index: 6905126 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2264. Min Range: -8.2264
Max Act: 6.9764. Min Act: -0.1700
Data Index: 7750929 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2264. Min Range: -8.2264
Max Act: 6.9764. Min Act: -0.1700
Data Index: 5262475 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2264. Min Range: -8.2264
Max Act: 6.9451. Min Act: -0.1700
Data Index: 1595904 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2264. Min Range: -8.2264
Max Act: 6.9139. Min Act: -0.1700
Data Index: 935771 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2264. Min Range: -8.2264
Max Act: 6.8826. Min Act: -0.1700
Data Index: 6687194 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2264. Min Range: -8.2264
Max Act: 6.8514. Min Act: -0.1700
Data Index: 4227726 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2264. Min Range: -8.2264
Max Act: 6.8514. Min Act: -0.1700
Data Index: 4247892 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2264. Min Range: -8.2264
Max Act: 6.8201. Min Act: -0.1700
Data Index: 3414069 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2264. Min Range: -8.2264
Max Act: 6.8201. Min Act: -0.1700
Data Index: 8091057 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2264. Min Range: -8.2264
Max Act: 6.7889. Min Act: -0.1700
Data Index: 4693192 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19