Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4671 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4823. Min Range: -8.4823
Max Act: 8.4823. Min Act: -0.1700
Data Index: 3318764 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4823. Min Range: -8.4823
Max Act: 8.4198. Min Act: -0.1700
Data Index: 6802249 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4823. Min Range: -8.4823
Max Act: 8.1698. Min Act: -0.1700
Data Index: 8303060 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4823. Min Range: -8.4823
Max Act: 8.1073. Min Act: -0.1700
Data Index: 4157485 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.9823. Min Act: -0.1700
Data Index: 2112889 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.9823. Min Act: -0.1700
Data Index: 608194 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.9823. Min Act: -0.1700
Data Index: 1771274 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.9823. Min Act: -0.1700
Data Index: 1986647 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.9823. Min Act: -0.1700
Data Index: 5158591 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.9198. Min Act: -0.1700
Data Index: 5589506 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.8573. Min Act: -0.1700
Data Index: 7973633 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.8573. Min Act: -0.1700
Data Index: 7691344 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.7948. Min Act: -0.1700
Data Index: 2115792 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.8573. Min Act: -0.1700
Data Index: 5863831 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.7948. Min Act: -0.1700
Data Index: 6677372 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.7948. Min Act: -0.1700
Data Index: 4572631 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.7323. Min Act: -0.1700
Data Index: 1519132 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.7323. Min Act: -0.1700
Data Index: 7964089 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.7323. Min Act: -0.1700
Data Index: 6934796 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4823. Min Range: -8.4823
Max Act: 7.7323. Min Act: -0.1700
Data Index: 4978078 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19