Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 751 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.6126. Min Act: -0.1700
Data Index: 7737607 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.4564. Min Act: -0.1700
Data Index: 1373408 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3938. Min Act: -0.1700
Data Index: 6081678 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3938. Min Act: -0.1700
Data Index: 6323494 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3938. Min Act: -0.1700
Data Index: 7318852 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3938. Min Act: -0.1700
Data Index: 4820737 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3938. Min Act: -0.1700
Data Index: 1473868 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3001. Min Act: -0.1700
Data Index: 2172686 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3313. Min Act: -0.1700
Data Index: 1904672 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3001. Min Act: -0.1700
Data Index: 2565037 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.2688. Min Act: -0.1700
Data Index: 4955053 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3001. Min Act: -0.1700
Data Index: 5576293 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.2063. Min Act: -0.1700
Data Index: 5962739 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.2376. Min Act: -0.1700
Data Index: 7169584 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.2376. Min Act: -0.1700
Data Index: 8114932 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.2063. Min Act: -0.1700
Data Index: 2781284 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.1751. Min Act: -0.1700
Data Index: 559868 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.2063. Min Act: -0.1700
Data Index: 7102658 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.2063. Min Act: -0.1700
Data Index: 4572949 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.1751. Min Act: -0.1700
Data Index: 3044386 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19