Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 802 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3141. Min Range: -6.3141
Max Act: 6.3141. Min Act: -0.1700
Data Index: 1672818 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3141. Min Range: -6.3141
Max Act: 6.2516. Min Act: -0.1700
Data Index: 4615802 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3141. Min Range: -6.3141
Max Act: 6.1266. Min Act: -0.1700
Data Index: 3624159 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3141. Min Range: -6.3141
Max Act: 6.0641. Min Act: -0.1700
Data Index: 6599697 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.9703. Min Act: -0.1700
Data Index: 700280 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.9703. Min Act: -0.1700
Data Index: 243431 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.9391. Min Act: -0.1700
Data Index: 7023607 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.9391. Min Act: -0.1700
Data Index: 4998197 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.8453. Min Act: -0.1700
Data Index: 4073160 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.8453. Min Act: -0.1700
Data Index: 2905521 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.8141. Min Act: -0.1700
Data Index: 1792189 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.8141. Min Act: -0.1700
Data Index: 6962889 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.8141. Min Act: -0.1700
Data Index: 8726598 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.7516. Min Act: -0.1700
Data Index: 4189587 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.7203. Min Act: -0.1700
Data Index: 4058308 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.7203. Min Act: -0.1700
Data Index: 6995226 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.7203. Min Act: -0.1700
Data Index: 1825610 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.6891. Min Act: -0.1700
Data Index: 6449296 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.6891. Min Act: -0.1700
Data Index: 1174596 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3141. Min Range: -6.3141
Max Act: 5.7203. Min Act: -0.1700
Data Index: 322778 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19