Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.8187. Min Act: -0.1700
Data Index: 7344837 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.6624. Min Act: -0.1700
Data Index: 4994257 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.6624. Min Act: -0.1700
Data Index: 42236 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.5999. Min Act: -0.1700
Data Index: 8544388 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.5999. Min Act: -0.1700
Data Index: 2648991 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.5999. Min Act: -0.1700
Data Index: 8552679 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.4749. Min Act: -0.1700
Data Index: 6039547 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.4124. Min Act: -0.1700
Data Index: 4093470 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.4437. Min Act: -0.1700
Data Index: 948469 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.4124. Min Act: -0.1700
Data Index: 7707089 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.3812. Min Act: -0.1700
Data Index: 5037572 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.3499. Min Act: -0.1700
Data Index: 5494699 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.3187. Min Act: -0.1700
Data Index: 371602 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.3187. Min Act: -0.1700
Data Index: 4766782 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.2874. Min Act: -0.1700
Data Index: 1565244 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.1937. Min Act: -0.1700
Data Index: 7022048 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.2249. Min Act: -0.1700
Data Index: 3981963 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.1937. Min Act: -0.1700
Data Index: 2911603 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.1937. Min Act: -0.1700
Data Index: 2409766 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8187. Min Range: -5.8187
Max Act: 5.1624. Min Act: -0.1700
Data Index: 557612 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19