Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2534 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4352. Min Range: -5.4352
Max Act: 5.4352. Min Act: -0.1700
Data Index: 6602286 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4352. Min Range: -5.4352
Max Act: 5.3727. Min Act: -0.1700
Data Index: 3401594 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4352. Min Range: -5.4352
Max Act: 5.1852. Min Act: -0.1700
Data Index: 2088704 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4352. Min Range: -5.4352
Max Act: 5.1540. Min Act: -0.1700
Data Index: 1092640 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4352. Min Range: -5.4352
Max Act: 5.1227. Min Act: -0.1700
Data Index: 6347888 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4352. Min Range: -5.4352
Max Act: 5.1227. Min Act: -0.1700
Data Index: 1420027 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4352. Min Range: -5.4352
Max Act: 5.0915. Min Act: -0.1700
Data Index: 3716220 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4352. Min Range: -5.4352
Max Act: 5.0602. Min Act: -0.1700
Data Index: 6984162 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4352. Min Range: -5.4352
Max Act: 5.0915. Min Act: -0.1700
Data Index: 3081216 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4352. Min Range: -5.4352
Max Act: 5.0290. Min Act: -0.1700
Data Index: 5201860 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4352. Min Range: -5.4352
Max Act: 5.0290. Min Act: -0.1700
Data Index: 5164216 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4352. Min Range: -5.4352
Max Act: 4.9977. Min Act: -0.1700
Data Index: 8552425 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4352. Min Range: -5.4352
Max Act: 4.9977. Min Act: -0.1700
Data Index: 6382522 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4352. Min Range: -5.4352
Max Act: 4.9977. Min Act: -0.1700
Data Index: 4850087 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4352. Min Range: -5.4352
Max Act: 4.9665. Min Act: -0.1700
Data Index: 5669002 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4352. Min Range: -5.4352
Max Act: 4.9352. Min Act: -0.1700
Data Index: 209841 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4352. Min Range: -5.4352
Max Act: 4.9352. Min Act: -0.1700
Data Index: 3072945 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4352. Min Range: -5.4352
Max Act: 4.9352. Min Act: -0.1700
Data Index: 4656666 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4352. Min Range: -5.4352
Max Act: 4.9352. Min Act: -0.1700
Data Index: 5464917 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4352. Min Range: -5.4352
Max Act: 4.9040. Min Act: -0.1700
Data Index: 8370711 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19