Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5147 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.7185. Min Act: -0.1700
Data Index: 5560216 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.6560. Min Act: -0.1700
Data Index: 697501 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.4372. Min Act: -0.1700
Data Index: 6959254 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.4060. Min Act: -0.1700
Data Index: 4073371 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.3122. Min Act: -0.1700
Data Index: 1397596 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.2810. Min Act: -0.1700
Data Index: 3525201 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.2497. Min Act: -0.1700
Data Index: 7943515 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.2185. Min Act: -0.1700
Data Index: 5689869 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.2185. Min Act: -0.1700
Data Index: 6106698 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.1872. Min Act: -0.1700
Data Index: 883884 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.1560. Min Act: -0.1700
Data Index: 2607716 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.1560. Min Act: -0.1700
Data Index: 4705337 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.1560. Min Act: -0.1700
Data Index: 8696119 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.0935. Min Act: -0.1700
Data Index: 7004411 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.1247. Min Act: -0.1700
Data Index: 6711558 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.1560. Min Act: -0.1700
Data Index: 6206953 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.1247. Min Act: -0.1700
Data Index: 4822955 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.1247. Min Act: -0.1700
Data Index: 5977821 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.1247. Min Act: -0.1700
Data Index: 4586845 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7185. Min Range: -5.7185
Max Act: 5.0935. Min Act: -0.1700
Data Index: 913629 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19