Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.7002. Min Act: -0.1700
Data Index: 2051214 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.6377. Min Act: -0.1700
Data Index: 5945659 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.5437. Min Act: -0.1700
Data Index: 4429980 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.5124. Min Act: -0.1700
Data Index: 706974 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.5124. Min Act: -0.1700
Data Index: 5292254 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.5124. Min Act: -0.1700
Data Index: 5218081 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.4811. Min Act: -0.1700
Data Index: 8684981 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.4654. Min Act: -0.1700
Data Index: 2000665 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.4654. Min Act: -0.1700
Data Index: 5576544 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.4654. Min Act: -0.1700
Data Index: 3476024 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.4654. Min Act: -0.1700
Data Index: 6883576 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.4498. Min Act: -0.1700
Data Index: 383747 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.4498. Min Act: -0.1700
Data Index: 4272934 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.4341. Min Act: -0.1700
Data Index: 1663645 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.4184. Min Act: -0.1700
Data Index: 351594 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.4184. Min Act: -0.1700
Data Index: 3013084 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.4184. Min Act: -0.1700
Data Index: 2038005 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.4027. Min Act: -0.1700
Data Index: 6095342 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.4027. Min Act: -0.1700
Data Index: 4305816 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7002. Min Range: -3.7002
Max Act: 3.4184. Min Act: -0.1700
Data Index: 4854670 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19