Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 448 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1501. Min Range: -5.1501
Max Act: 5.1501. Min Act: -0.1700
Data Index: 5938543 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1501. Min Range: -5.1501
Max Act: 5.1189. Min Act: -0.1700
Data Index: 6502238 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1501. Min Range: -5.1501
Max Act: 5.0876. Min Act: -0.1700
Data Index: 7124640 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1501. Min Range: -5.1501
Max Act: 5.0564. Min Act: -0.1700
Data Index: 1341355 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1501. Min Range: -5.1501
Max Act: 5.0564. Min Act: -0.1700
Data Index: 3695160 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1501. Min Range: -5.1501
Max Act: 5.0876. Min Act: -0.1700
Data Index: 2376900 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1501. Min Range: -5.1501
Max Act: 5.0251. Min Act: -0.1700
Data Index: 8623869 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1501. Min Range: -5.1501
Max Act: 5.0564. Min Act: -0.1700
Data Index: 6292780 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1501. Min Range: -5.1501
Max Act: 5.0251. Min Act: -0.1700
Data Index: 4707924 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1501. Min Range: -5.1501
Max Act: 4.9939. Min Act: -0.1700
Data Index: 2065758 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1501. Min Range: -5.1501
Max Act: 4.9939. Min Act: -0.1700
Data Index: 1425478 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1501. Min Range: -5.1501
Max Act: 4.9939. Min Act: -0.1700
Data Index: 3306596 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1501. Min Range: -5.1501
Max Act: 4.9939. Min Act: -0.1700
Data Index: 5145047 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1501. Min Range: -5.1501
Max Act: 4.9626. Min Act: -0.1700
Data Index: 1153673 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1501. Min Range: -5.1501
Max Act: 4.9626. Min Act: -0.1700
Data Index: 893952 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1501. Min Range: -5.1501
Max Act: 4.9626. Min Act: -0.1700
Data Index: 3655119 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1501. Min Range: -5.1501
Max Act: 4.9626. Min Act: -0.1700
Data Index: 5621514 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1501. Min Range: -5.1501
Max Act: 4.9314. Min Act: -0.1700
Data Index: 7123450 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1501. Min Range: -5.1501
Max Act: 4.9626. Min Act: -0.1700
Data Index: 6638379 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1501. Min Range: -5.1501
Max Act: 4.9314. Min Act: -0.1700
Data Index: 2210230 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19