Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2841 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0310. Min Range: -1.0310
Max Act: 1.0310. Min Act: -0.1700
Data Index: 4648097 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8929. Min Act: -0.1700
Data Index: 5161073 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8844. Min Act: -0.1700
Data Index: 654940 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8929. Min Act: -0.1700
Data Index: 433830 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8588. Min Act: -0.1700
Data Index: 8492355 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8588. Min Act: -0.1700
Data Index: 3450396 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8588. Min Act: -0.1700
Data Index: 2071847 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8673. Min Act: -0.1700
Data Index: 8618331 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8419. Min Act: -0.1700
Data Index: 4107499 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8504. Min Act: -0.1700
Data Index: 4035557 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8334. Min Act: -0.1700
Data Index: 8525647 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8334. Min Act: -0.1700
Data Index: 1446176 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8334. Min Act: -0.1700
Data Index: 1065595 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8334. Min Act: -0.1700
Data Index: 481572 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8250. Min Act: -0.1700
Data Index: 5914771 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8166. Min Act: -0.1700
Data Index: 6995094 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8334. Min Act: -0.1700
Data Index: 4903111 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8334. Min Act: -0.1700
Data Index: 1979628 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8250. Min Act: -0.1700
Data Index: 4635737 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0310. Min Range: -1.0310
Max Act: 0.8166. Min Act: -0.1700
Data Index: 4871402 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19