Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2096 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.6698. Min Act: -0.1700
Data Index: 5308292 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.6073. Min Act: -0.1700
Data Index: 3088314 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.5135. Min Act: -0.1700
Data Index: 4443330 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.5448. Min Act: -0.1700
Data Index: 2538969 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.4823. Min Act: -0.1700
Data Index: 7357033 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.4510. Min Act: -0.1700
Data Index: 5308296 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.4198. Min Act: -0.1700
Data Index: 5015693 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.4198. Min Act: -0.1700
Data Index: 2218432 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.3573. Min Act: -0.1700
Data Index: 1664588 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.3573. Min Act: -0.1700
Data Index: 5812864 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.3573. Min Act: -0.1700
Data Index: 808811 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.3260. Min Act: -0.1700
Data Index: 7811552 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.3260. Min Act: -0.1700
Data Index: 6392320 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.2948. Min Act: -0.1700
Data Index: 6216118 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.2948. Min Act: -0.1700
Data Index: 1811262 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.2948. Min Act: -0.1700
Data Index: 1793062 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.2948. Min Act: -0.1700
Data Index: 2933489 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.3260. Min Act: -0.1700
Data Index: 5992715 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.2948. Min Act: -0.1700
Data Index: 4327100 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6698. Min Range: -5.6698
Max Act: 5.2948. Min Act: -0.1700
Data Index: 7232085 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19