Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2818 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.8717. Min Act: -0.1700
Data Index: 7550903 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.8717. Min Act: -0.1700
Data Index: 7214262 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.8092. Min Act: -0.1700
Data Index: 1317171 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.7780. Min Act: -0.1700
Data Index: 5459793 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.7155. Min Act: -0.1700
Data Index: 6484481 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.6530. Min Act: -0.1700
Data Index: 4596529 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.6217. Min Act: -0.1700
Data Index: 5774925 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.5905. Min Act: -0.1700
Data Index: 7259841 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.6217. Min Act: -0.1700
Data Index: 548445 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.5592. Min Act: -0.1700
Data Index: 1172872 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.5905. Min Act: -0.1700
Data Index: 4324503 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.5280. Min Act: -0.1700
Data Index: 3366059 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.5280. Min Act: -0.1700
Data Index: 2957515 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.5280. Min Act: -0.1700
Data Index: 4236006 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.5280. Min Act: -0.1700
Data Index: 6581436 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.4967. Min Act: -0.1700
Data Index: 2478222 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.4967. Min Act: -0.1700
Data Index: 6443328 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.4655. Min Act: -0.1700
Data Index: 3155244 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.4655. Min Act: -0.1700
Data Index: 5453157 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8717. Min Range: -5.8717
Max Act: 5.4655. Min Act: -0.1700
Data Index: 281212 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19