Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1089 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.2283. Min Act: -0.1700
Data Index: 4116273 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.1658. Min Act: -0.1700
Data Index: 6892530 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.1971. Min Act: -0.1700
Data Index: 2485522 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.1346. Min Act: -0.1700
Data Index: 6130568 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.0721. Min Act: -0.1700
Data Index: 5593547 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.0721. Min Act: -0.1700
Data Index: 4251653 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.0721. Min Act: -0.1700
Data Index: 3925893 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.0408. Min Act: -0.1700
Data Index: 5773299 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.0721. Min Act: -0.1700
Data Index: 7645655 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.0721. Min Act: -0.1700
Data Index: 5593546 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.0408. Min Act: -0.1700
Data Index: 1333625 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.0408. Min Act: -0.1700
Data Index: 271897 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.0408. Min Act: -0.1700
Data Index: 2343778 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.0408. Min Act: -0.1700
Data Index: 2746641 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.0096. Min Act: -0.1700
Data Index: 5221121 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.0096. Min Act: -0.1700
Data Index: 8249795 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2283. Min Range: -5.2283
Max Act: 5.0408. Min Act: -0.1700
Data Index: 4093519 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2283. Min Range: -5.2283
Max Act: 4.9783. Min Act: -0.1700
Data Index: 5753616 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2283. Min Range: -5.2283
Max Act: 4.9783. Min Act: -0.1700
Data Index: 3271600 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2283. Min Range: -5.2283
Max Act: 4.9783. Min Act: -0.1700
Data Index: 3938171 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19