Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1981 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1474. Min Range: -5.1474
Max Act: 5.1474. Min Act: -0.1700
Data Index: 8443825 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.8662. Min Act: -0.1700
Data Index: 4779458 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.8349. Min Act: -0.1700
Data Index: 4183050 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.8037. Min Act: -0.1700
Data Index: 991737 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.8037. Min Act: -0.1700
Data Index: 3446882 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.7412. Min Act: -0.1700
Data Index: 1797408 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.7412. Min Act: -0.1700
Data Index: 4945697 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.7099. Min Act: -0.1700
Data Index: 1245297 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.7099. Min Act: -0.1700
Data Index: 3282302 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.7099. Min Act: -0.1700
Data Index: 4579953 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.7099. Min Act: -0.1700
Data Index: 6709292 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.7099. Min Act: -0.1700
Data Index: 7004240 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.6787. Min Act: -0.1700
Data Index: 8482130 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.6787. Min Act: -0.1700
Data Index: 3270401 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.6787. Min Act: -0.1700
Data Index: 8366205 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.6787. Min Act: -0.1700
Data Index: 2118432 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.6474. Min Act: -0.1700
Data Index: 6812558 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.6474. Min Act: -0.1700
Data Index: 1578233 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.6474. Min Act: -0.1700
Data Index: 5758549 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1474. Min Range: -5.1474
Max Act: 4.6474. Min Act: -0.1700
Data Index: 5796976 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19