Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5249 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.7626. Min Act: -0.1700
Data Index: 2451163 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.6063. Min Act: -0.1700
Data Index: 35365 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.5438. Min Act: -0.1700
Data Index: 6770162 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.4813. Min Act: -0.1700
Data Index: 6758332 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.4188. Min Act: -0.1700
Data Index: 5777771 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.3876. Min Act: -0.1700
Data Index: 5250223 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.3876. Min Act: -0.1700
Data Index: 6770165 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.3876. Min Act: -0.1700
Data Index: 1328186 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.3876. Min Act: -0.1700
Data Index: 5250225 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.3563. Min Act: -0.1700
Data Index: 8600965 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.3563. Min Act: -0.1700
Data Index: 7682539 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.3563. Min Act: -0.1700
Data Index: 2390762 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.3563. Min Act: -0.1700
Data Index: 4614345 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.3251. Min Act: -0.1700
Data Index: 6520919 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.2938. Min Act: -0.1700
Data Index: 1985246 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.2626. Min Act: -0.1700
Data Index: 8012401 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.2626. Min Act: -0.1700
Data Index: 1328184 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.2626. Min Act: -0.1700
Data Index: 8122975 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.2001. Min Act: -0.1700
Data Index: 5042273 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7626. Min Range: -4.7626
Max Act: 4.2313. Min Act: -0.1700
Data Index: 3026264 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19