Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5463 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0143. Min Range: -6.0143
Max Act: 6.0143. Min Act: -0.1700
Data Index: 8267690 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.8893. Min Act: -0.1700
Data Index: 4478158 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.8893. Min Act: -0.1700
Data Index: 4311260 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.8581. Min Act: -0.1700
Data Index: 5884537 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.8268. Min Act: -0.1700
Data Index: 2094193 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.8268. Min Act: -0.1700
Data Index: 2259936 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.7643. Min Act: -0.1700
Data Index: 7898456 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.7018. Min Act: -0.1700
Data Index: 7030783 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.7018. Min Act: -0.1700
Data Index: 6751849 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.7018. Min Act: -0.1700
Data Index: 2527917 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.6393. Min Act: -0.1700
Data Index: 2180219 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.6393. Min Act: -0.1700
Data Index: 524958 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.6393. Min Act: -0.1700
Data Index: 673618 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.6393. Min Act: -0.1700
Data Index: 4861058 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.6081. Min Act: -0.1700
Data Index: 3216830 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.6393. Min Act: -0.1700
Data Index: 976994 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.5768. Min Act: -0.1700
Data Index: 945887 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.6081. Min Act: -0.1700
Data Index: 8723615 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.6081. Min Act: -0.1700
Data Index: 3763594 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0143. Min Range: -6.0143
Max Act: 5.6081. Min Act: -0.1700
Data Index: 3485304 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19