Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3742 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0286. Min Range: -6.0286
Max Act: 6.0286. Min Act: -0.1700
Data Index: 4433573 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.9661. Min Act: -0.1700
Data Index: 4351888 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.9036. Min Act: -0.1700
Data Index: 8356217 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.8411. Min Act: -0.1700
Data Index: 1450034 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.7786. Min Act: -0.1700
Data Index: 2914318 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.7161. Min Act: -0.1700
Data Index: 3774740 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.6849. Min Act: -0.1700
Data Index: 3818462 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.6536. Min Act: -0.1700
Data Index: 2146192 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.6536. Min Act: -0.1700
Data Index: 8801392 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.6536. Min Act: -0.1700
Data Index: 8113072 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.6536. Min Act: -0.1700
Data Index: 2171275 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.6224. Min Act: -0.1700
Data Index: 3458414 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.6224. Min Act: -0.1700
Data Index: 28702 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.5911. Min Act: -0.1700
Data Index: 8328234 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.6224. Min Act: -0.1700
Data Index: 89190 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.5911. Min Act: -0.1700
Data Index: 7415348 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.5599. Min Act: -0.1700
Data Index: 2931996 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.5599. Min Act: -0.1700
Data Index: 3082425 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.5286. Min Act: -0.1700
Data Index: 3263385 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0286. Min Range: -6.0286
Max Act: 5.4974. Min Act: -0.1700
Data Index: 3686970 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19