Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3638 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5185. Min Range: -9.5185
Max Act: 9.5185. Min Act: -0.1700
Data Index: 8724959 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5185. Min Range: -9.5185
Max Act: 9.0185. Min Act: -0.1700
Data Index: 5024634 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5185. Min Range: -9.5185
Max Act: 9.0185. Min Act: -0.1700
Data Index: 6525307 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.8935. Min Act: -0.1700
Data Index: 152551 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.8935. Min Act: -0.1700
Data Index: 5109674 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.8935. Min Act: -0.1700
Data Index: 7073636 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.8310. Min Act: -0.1700
Data Index: 8153704 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.8310. Min Act: -0.1700
Data Index: 1367839 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.7685. Min Act: -0.1700
Data Index: 4653350 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.7685. Min Act: -0.1700
Data Index: 2200963 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.7685. Min Act: -0.1700
Data Index: 6048170 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.7060. Min Act: -0.1700
Data Index: 8507476 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.7060. Min Act: -0.1700
Data Index: 8758769 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.7060. Min Act: -0.1700
Data Index: 1109486 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.7060. Min Act: -0.1700
Data Index: 4419671 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.7685. Min Act: -0.1700
Data Index: 2874883 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.6435. Min Act: -0.1700
Data Index: 7314600 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.6435. Min Act: -0.1700
Data Index: 5943870 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.5810. Min Act: -0.1700
Data Index: 7434769 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5185. Min Range: -9.5185
Max Act: 8.5810. Min Act: -0.1700
Data Index: 7489266 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19