Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 777 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2137. Min Range: -9.2137
Max Act: 9.2137. Min Act: -0.1700
Data Index: 8160096 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2137. Min Range: -9.2137
Max Act: 9.0887. Min Act: -0.1700
Data Index: 2653927 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.9637. Min Act: -0.1700
Data Index: 3308424 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.8387. Min Act: -0.1700
Data Index: 747681 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.8387. Min Act: -0.1700
Data Index: 1928522 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.7137. Min Act: -0.1700
Data Index: 201037 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.6512. Min Act: -0.1700
Data Index: 6060152 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.6512. Min Act: -0.1700
Data Index: 4727690 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.5887. Min Act: -0.1700
Data Index: 5704489 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.4637. Min Act: -0.1700
Data Index: 3682002 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.4012. Min Act: -0.1700
Data Index: 1787687 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.4012. Min Act: -0.1700
Data Index: 3888092 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.4012. Min Act: -0.1700
Data Index: 4315263 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.4012. Min Act: -0.1700
Data Index: 4958911 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.3387. Min Act: -0.1700
Data Index: 5172692 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.3387. Min Act: -0.1700
Data Index: 6172210 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.3387. Min Act: -0.1700
Data Index: 4487850 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.3387. Min Act: -0.1700
Data Index: 8060161 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.2137. Min Act: -0.1700
Data Index: 6031564 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2137. Min Range: -9.2137
Max Act: 8.2762. Min Act: -0.1700
Data Index: 1743058 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19