Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5265 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4677. Min Range: -7.4677
Max Act: 7.4677. Min Act: -0.1700
Data Index: 1688932 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4677. Min Range: -7.4677
Max Act: 7.2489. Min Act: -0.1700
Data Index: 6667597 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4677. Min Range: -7.4677
Max Act: 7.2177. Min Act: -0.1700
Data Index: 2389364 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4677. Min Range: -7.4677
Max Act: 7.1552. Min Act: -0.1700
Data Index: 6415725 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4677. Min Range: -7.4677
Max Act: 7.1552. Min Act: -0.1700
Data Index: 1503484 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4677. Min Range: -7.4677
Max Act: 7.1552. Min Act: -0.1700
Data Index: 2380093 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4677. Min Range: -7.4677
Max Act: 7.0927. Min Act: -0.1700
Data Index: 2499801 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4677. Min Range: -7.4677
Max Act: 7.0614. Min Act: -0.1700
Data Index: 8287649 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4677. Min Range: -7.4677
Max Act: 7.0302. Min Act: -0.1700
Data Index: 8795970 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4677. Min Range: -7.4677
Max Act: 7.0302. Min Act: -0.1700
Data Index: 5201711 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4677. Min Range: -7.4677
Max Act: 6.9052. Min Act: -0.1700
Data Index: 7191105 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4677. Min Range: -7.4677
Max Act: 6.9364. Min Act: -0.1700
Data Index: 6440281 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4677. Min Range: -7.4677
Max Act: 6.9364. Min Act: -0.1700
Data Index: 6712250 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4677. Min Range: -7.4677
Max Act: 6.9364. Min Act: -0.1700
Data Index: 8012882 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4677. Min Range: -7.4677
Max Act: 6.9364. Min Act: -0.1700
Data Index: 2534701 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4677. Min Range: -7.4677
Max Act: 6.8739. Min Act: -0.1700
Data Index: 7170058 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4677. Min Range: -7.4677
Max Act: 6.9052. Min Act: -0.1700
Data Index: 4948467 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4677. Min Range: -7.4677
Max Act: 6.8739. Min Act: -0.1700
Data Index: 527371 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4677. Min Range: -7.4677
Max Act: 6.8739. Min Act: -0.1700
Data Index: 7895227 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4677. Min Range: -7.4677
Max Act: 6.8739. Min Act: -0.1700
Data Index: 479455 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19