Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 656 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.9444. Min Act: -0.1700
Data Index: 4284296 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.9444. Min Act: -0.1700
Data Index: 3304020 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.9131. Min Act: -0.1700
Data Index: 8561748 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.9131. Min Act: -0.1700
Data Index: 2508245 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.8194. Min Act: -0.1700
Data Index: 8538152 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.8194. Min Act: -0.1700
Data Index: 1969578 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.8194. Min Act: -0.1700
Data Index: 5480772 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.7881. Min Act: -0.1700
Data Index: 2921890 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.7569. Min Act: -0.1700
Data Index: 5483699 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.7569. Min Act: -0.1700
Data Index: 8011481 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.7256. Min Act: -0.1700
Data Index: 5477487 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.7256. Min Act: -0.1700
Data Index: 1856270 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.7256. Min Act: -0.1700
Data Index: 7907915 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.7256. Min Act: -0.1700
Data Index: 5826660 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.7256. Min Act: -0.1700
Data Index: 564142 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.7256. Min Act: -0.1700
Data Index: 7861805 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.7256. Min Act: -0.1700
Data Index: 402721 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.6944. Min Act: -0.1700
Data Index: 4746198 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.6944. Min Act: -0.1700
Data Index: 5010966 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9444. Min Range: -5.9444
Max Act: 5.6944. Min Act: -0.1700
Data Index: 3905870 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19