Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 747 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1954. Min Range: -7.1954
Max Act: 7.1954. Min Act: -0.1700
Data Index: 7325751 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.6329. Min Act: -0.1700
Data Index: 2598297 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.6016. Min Act: -0.1700
Data Index: 2502680 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.5391. Min Act: -0.1700
Data Index: 145891 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.3829. Min Act: -0.1700
Data Index: 318422 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.3829. Min Act: -0.1700
Data Index: 3285101 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.2891. Min Act: -0.1700
Data Index: 510681 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.2891. Min Act: -0.1700
Data Index: 7310996 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.2891. Min Act: -0.1700
Data Index: 7834970 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.2266. Min Act: -0.1700
Data Index: 488620 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.2579. Min Act: -0.1700
Data Index: 6082466 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.1329. Min Act: -0.1700
Data Index: 342399 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.1329. Min Act: -0.1700
Data Index: 8793022 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.1329. Min Act: -0.1700
Data Index: 5488342 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.1016. Min Act: -0.1700
Data Index: 6791476 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.1016. Min Act: -0.1700
Data Index: 8242845 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.1016. Min Act: -0.1700
Data Index: 6647141 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.1016. Min Act: -0.1700
Data Index: 6226332 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.1016. Min Act: -0.1700
Data Index: 2205930 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1954. Min Range: -7.1954
Max Act: 6.0704. Min Act: -0.1700
Data Index: 3958640 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19