Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3922 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.1577. Min Act: -0.1700
Data Index: 2794607 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.1410. Min Act: -0.1700
Data Index: 3799172 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.1243. Min Act: -0.1700
Data Index: 2220783 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.1243. Min Act: -0.1700
Data Index: 3508680 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.1243. Min Act: -0.1700
Data Index: 3256463 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.1243. Min Act: -0.1700
Data Index: 3245562 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.0908. Min Act: -0.1700
Data Index: 6369663 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.0908. Min Act: -0.1700
Data Index: 3040398 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.0741. Min Act: -0.1700
Data Index: 5367585 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.0741. Min Act: -0.1700
Data Index: 6945192 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.0573. Min Act: -0.1700
Data Index: 1888238 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.0573. Min Act: -0.1700
Data Index: 8564453 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.0573. Min Act: -0.1700
Data Index: 4037440 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.0573. Min Act: -0.1700
Data Index: 2993638 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.0741. Min Act: -0.1700
Data Index: 8079654 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.0573. Min Act: -0.1700
Data Index: 7936616 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.0573. Min Act: -0.1700
Data Index: 4128885 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.0404. Min Act: -0.1700
Data Index: 1121591 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.0404. Min Act: -0.1700
Data Index: 1946262 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1577. Min Range: -2.1577
Max Act: 2.0404. Min Act: -0.1700
Data Index: 1707046 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19