Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2563 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4813. Min Range: -5.4813
Max Act: 5.4813. Min Act: -0.1700
Data Index: 8580873 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.7938. Min Act: -0.1700
Data Index: 6478570 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.5751. Min Act: -0.1700
Data Index: 5832008 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.5751. Min Act: -0.1700
Data Index: 3910630 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.5438. Min Act: -0.1700
Data Index: 1725480 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.5438. Min Act: -0.1700
Data Index: 7926481 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.5438. Min Act: -0.1700
Data Index: 2761145 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.4813. Min Act: -0.1700
Data Index: 8601004 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.4501. Min Act: -0.1700
Data Index: 3046241 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.4501. Min Act: -0.1700
Data Index: 5867451 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.4501. Min Act: -0.1700
Data Index: 1472369 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.3876. Min Act: -0.1700
Data Index: 8060413 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.4188. Min Act: -0.1700
Data Index: 3504284 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.4188. Min Act: -0.1700
Data Index: 8024318 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.3563. Min Act: -0.1700
Data Index: 2404182 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.3876. Min Act: -0.1700
Data Index: 3577755 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.3251. Min Act: -0.1700
Data Index: 8747698 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.3251. Min Act: -0.1700
Data Index: 4017701 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.2626. Min Act: -0.1700
Data Index: 7756767 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4813. Min Range: -5.4813
Max Act: 4.2938. Min Act: -0.1700
Data Index: 1552367 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19