Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3488 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4258. Min Range: -10.4258
Max Act: 10.4258. Min Act: -0.1700
Data Index: 1195030 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.8008. Min Act: -0.1700
Data Index: 7335871 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.7383. Min Act: -0.1700
Data Index: 5040140 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.6133. Min Act: -0.1700
Data Index: 6106400 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.6758. Min Act: -0.1700
Data Index: 7961060 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.6758. Min Act: -0.1700
Data Index: 4861740 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.6133. Min Act: -0.1700
Data Index: 2444826 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.6133. Min Act: -0.1700
Data Index: 6708296 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.6133. Min Act: -0.1700
Data Index: 2106821 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.6133. Min Act: -0.1700
Data Index: 72355 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.5508. Min Act: -0.1700
Data Index: 5955673 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.5508. Min Act: -0.1700
Data Index: 4979374 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.4883. Min Act: -0.1700
Data Index: 1496760 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.4883. Min Act: -0.1700
Data Index: 7900590 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.4883. Min Act: -0.1700
Data Index: 4237059 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.4258. Min Act: -0.1700
Data Index: 8609076 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.4258. Min Act: -0.1700
Data Index: 8434614 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.3633. Min Act: -0.1700
Data Index: 2793513 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.3008. Min Act: -0.1700
Data Index: 5221227 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4258. Min Range: -10.4258
Max Act: 9.3633. Min Act: -0.1700
Data Index: 572009 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19