Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2857 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2144. Min Range: -7.2144
Max Act: 7.2144. Min Act: -0.1700
Data Index: 3434318 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2144. Min Range: -7.2144
Max Act: 7.0894. Min Act: -0.1700
Data Index: 8389076 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.9644. Min Act: -0.1700
Data Index: 58652 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.9019. Min Act: -0.1700
Data Index: 3204405 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.8707. Min Act: -0.1700
Data Index: 2791753 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.8707. Min Act: -0.1700
Data Index: 1419586 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.8082. Min Act: -0.1700
Data Index: 1366505 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.8082. Min Act: -0.1700
Data Index: 7130785 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.7457. Min Act: -0.1700
Data Index: 3894447 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.6832. Min Act: -0.1700
Data Index: 6211198 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.7144. Min Act: -0.1700
Data Index: 5098993 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.6207. Min Act: -0.1700
Data Index: 8464100 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.5582. Min Act: -0.1700
Data Index: 6335207 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.5582. Min Act: -0.1700
Data Index: 371423 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.5582. Min Act: -0.1700
Data Index: 2719904 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.5894. Min Act: -0.1700
Data Index: 371420 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.5894. Min Act: -0.1700
Data Index: 4319569 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.5582. Min Act: -0.1700
Data Index: 5139354 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.5269. Min Act: -0.1700
Data Index: 5816756 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2144. Min Range: -7.2144
Max Act: 6.4957. Min Act: -0.1700
Data Index: 5139351 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19