Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1977 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0742. Min Range: -5.0742
Max Act: 5.0742. Min Act: -0.1700
Data Index: 1368848 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.9179. Min Act: -0.1700
Data Index: 6893020 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.8242. Min Act: -0.1700
Data Index: 6280690 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.8242. Min Act: -0.1700
Data Index: 5537604 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.7617. Min Act: -0.1700
Data Index: 2148882 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.7929. Min Act: -0.1700
Data Index: 7627536 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.7617. Min Act: -0.1700
Data Index: 8721479 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.7617. Min Act: -0.1700
Data Index: 2463940 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.7304. Min Act: -0.1700
Data Index: 2624253 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6992. Min Act: -0.1700
Data Index: 5285914 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6992. Min Act: -0.1700
Data Index: 3607870 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6992. Min Act: -0.1700
Data Index: 3169657 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6992. Min Act: -0.1700
Data Index: 333552 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.7304. Min Act: -0.1700
Data Index: 6803996 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6679. Min Act: -0.1700
Data Index: 1362916 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6992. Min Act: -0.1700
Data Index: 2624252 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6679. Min Act: -0.1700
Data Index: 1133160 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6367. Min Act: -0.1700
Data Index: 3554474 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6679. Min Act: -0.1700
Data Index: 2683917 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0742. Min Range: -5.0742
Max Act: 4.6367. Min Act: -0.1700
Data Index: 5792966 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19