Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3747 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3688. Min Range: -9.3688
Max Act: 9.3688. Min Act: -0.1700
Data Index: 3641711 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3688. Min Range: -9.3688
Max Act: 9.3688. Min Act: -0.1700
Data Index: 4231165 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3688. Min Range: -9.3688
Max Act: 9.3063. Min Act: -0.1700
Data Index: 6959105 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3688. Min Range: -9.3688
Max Act: 9.3063. Min Act: -0.1700
Data Index: 6005171 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3688. Min Range: -9.3688
Max Act: 9.2438. Min Act: -0.1700
Data Index: 773943 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3688. Min Range: -9.3688
Max Act: 9.2438. Min Act: -0.1700
Data Index: 5944047 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3688. Min Range: -9.3688
Max Act: 9.2438. Min Act: -0.1700
Data Index: 344777 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3688. Min Range: -9.3688
Max Act: 9.1813. Min Act: -0.1700
Data Index: 2438363 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3688. Min Range: -9.3688
Max Act: 9.1813. Min Act: -0.1700
Data Index: 605131 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3688. Min Range: -9.3688
Max Act: 9.1188. Min Act: -0.1700
Data Index: 3089218 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3688. Min Range: -9.3688
Max Act: 8.9938. Min Act: -0.1700
Data Index: 1586186 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3688. Min Range: -9.3688
Max Act: 8.9313. Min Act: -0.1700
Data Index: 4990590 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3688. Min Range: -9.3688
Max Act: 8.8688. Min Act: -0.1700
Data Index: 5235091 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3688. Min Range: -9.3688
Max Act: 8.8688. Min Act: -0.1700
Data Index: 5256298 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3688. Min Range: -9.3688
Max Act: 8.8688. Min Act: -0.1700
Data Index: 4600255 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3688. Min Range: -9.3688
Max Act: 8.8688. Min Act: -0.1700
Data Index: 2589752 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3688. Min Range: -9.3688
Max Act: 8.8063. Min Act: -0.1700
Data Index: 1405753 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3688. Min Range: -9.3688
Max Act: 8.8063. Min Act: -0.1700
Data Index: 6666967 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3688. Min Range: -9.3688
Max Act: 8.8063. Min Act: -0.1700
Data Index: 6852969 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3688. Min Range: -9.3688
Max Act: 8.8063. Min Act: -0.1700
Data Index: 4153967 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19