Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.6419. Min Act: -0.1700
Data Index: 5035222 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.5169. Min Act: -0.1700
Data Index: 7786263 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.5169. Min Act: -0.1700
Data Index: 7624217 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.4856. Min Act: -0.1700
Data Index: 2231766 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.4544. Min Act: -0.1700
Data Index: 8253117 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.4231. Min Act: -0.1700
Data Index: 2839736 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.3294. Min Act: -0.1700
Data Index: 3661371 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.2044. Min Act: -0.1700
Data Index: 608826 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.1731. Min Act: -0.1700
Data Index: 6787228 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.1419. Min Act: -0.1700
Data Index: 6209576 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.1106. Min Act: -0.1700
Data Index: 4575817 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.1106. Min Act: -0.1700
Data Index: 7894992 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.1106. Min Act: -0.1700
Data Index: 6225084 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.0794. Min Act: -0.1700
Data Index: 1572599 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.0794. Min Act: -0.1700
Data Index: 8466456 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.0794. Min Act: -0.1700
Data Index: 6734851 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.0794. Min Act: -0.1700
Data Index: 4220336 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6419. Min Range: -7.6419
Max Act: 7.0481. Min Act: -0.1700
Data Index: 8706855 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6419. Min Range: -7.6419
Max Act: 6.9856. Min Act: -0.1700
Data Index: 5300955 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6419. Min Range: -7.6419
Max Act: 6.9856. Min Act: -0.1700
Data Index: 4224695 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19