Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1985 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1250. Min Range: -5.1250
Max Act: 5.1250. Min Act: -0.1700
Data Index: 6309036 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.9688. Min Act: -0.1700
Data Index: 5376155 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.9375. Min Act: -0.1700
Data Index: 3202295 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.9063. Min Act: -0.1700
Data Index: 7278969 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.8438. Min Act: -0.1700
Data Index: 4165708 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.8125. Min Act: -0.1700
Data Index: 3108513 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.7813. Min Act: -0.1700
Data Index: 8405731 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.7500. Min Act: -0.1700
Data Index: 5967308 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.7500. Min Act: -0.1700
Data Index: 7843304 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.7188. Min Act: -0.1700
Data Index: 6311987 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.6875. Min Act: -0.1700
Data Index: 2552125 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.7188. Min Act: -0.1700
Data Index: 183763 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.6875. Min Act: -0.1700
Data Index: 7214593 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.7188. Min Act: -0.1700
Data Index: 3609016 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.7188. Min Act: -0.1700
Data Index: 2951486 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.6875. Min Act: -0.1700
Data Index: 8405723 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.6875. Min Act: -0.1700
Data Index: 7048023 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.6563. Min Act: -0.1700
Data Index: 1494496 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.6563. Min Act: -0.1700
Data Index: 1491228 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1250. Min Range: -5.1250
Max Act: 4.6563. Min Act: -0.1700
Data Index: 4064242 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19