Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2974 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.8946. Min Act: -0.1700
Data Index: 5101982 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.8321. Min Act: -0.1700
Data Index: 8143134 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.8321. Min Act: -0.1700
Data Index: 1049533 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.7696. Min Act: -0.1700
Data Index: 7227052 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.7696. Min Act: -0.1700
Data Index: 8354765 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.7071. Min Act: -0.1700
Data Index: 4214623 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.7071. Min Act: -0.1700
Data Index: 366825 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.6446. Min Act: -0.1700
Data Index: 7575441 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.5821. Min Act: -0.1700
Data Index: 2321190 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.5509. Min Act: -0.1700
Data Index: 5525691 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.5821. Min Act: -0.1700
Data Index: 4283598 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.5509. Min Act: -0.1700
Data Index: 7044606 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.5509. Min Act: -0.1700
Data Index: 8494998 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.5196. Min Act: -0.1700
Data Index: 6125586 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.4571. Min Act: -0.1700
Data Index: 7168806 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.4884. Min Act: -0.1700
Data Index: 7892719 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.4571. Min Act: -0.1700
Data Index: 6218795 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.4571. Min Act: -0.1700
Data Index: 1239487 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.4884. Min Act: -0.1700
Data Index: 4025261 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8946. Min Range: -7.8946
Max Act: 7.4571. Min Act: -0.1700
Data Index: 5217126 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19