Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2478 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.9425. Min Act: -0.1700
Data Index: 7014466 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.8174. Min Act: -0.1700
Data Index: 4399403 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.8174. Min Act: -0.1700
Data Index: 1636047 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.7861. Min Act: -0.1700
Data Index: 4862700 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.7549. Min Act: -0.1700
Data Index: 7155796 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.7236. Min Act: -0.1700
Data Index: 7655796 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.7236. Min Act: -0.1700
Data Index: 6447618 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.7236. Min Act: -0.1700
Data Index: 8271284 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.7236. Min Act: -0.1700
Data Index: 6417396 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.7236. Min Act: -0.1700
Data Index: 2387323 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.7236. Min Act: -0.1700
Data Index: 1545558 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.7236. Min Act: -0.1700
Data Index: 413016 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.6923. Min Act: -0.1700
Data Index: 1684677 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.7236. Min Act: -0.1700
Data Index: 5434218 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.6923. Min Act: -0.1700
Data Index: 677198 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.6923. Min Act: -0.1700
Data Index: 2322753 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.6923. Min Act: -0.1700
Data Index: 4081969 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.6923. Min Act: -0.1700
Data Index: 7068006 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.6610. Min Act: -0.1700
Data Index: 613135 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9425. Min Range: -3.9425
Max Act: 3.6923. Min Act: -0.1700
Data Index: 5632454 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19