Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3499 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6972. Min Act: -0.1700
Data Index: 5646755 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6972. Min Act: -0.1700
Data Index: 8374195 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6799. Min Act: -0.1700
Data Index: 8657023 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6712. Min Act: -0.1700
Data Index: 7829429 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6625. Min Act: -0.1700
Data Index: 5893137 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6712. Min Act: -0.1700
Data Index: 5712730 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6712. Min Act: -0.1700
Data Index: 8431909 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6625. Min Act: -0.1700
Data Index: 3471522 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6538. Min Act: -0.1700
Data Index: 1409005 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6451. Min Act: -0.1700
Data Index: 5262867 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6538. Min Act: -0.1700
Data Index: 1455510 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6538. Min Act: -0.1700
Data Index: 2584203 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6277. Min Act: -0.1700
Data Index: 7888038 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6277. Min Act: -0.1700
Data Index: 4183836 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6277. Min Act: -0.1700
Data Index: 2211602 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6102. Min Act: -0.1700
Data Index: 2663864 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6102. Min Act: -0.1700
Data Index: 5240171 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6102. Min Act: -0.1700
Data Index: 1658138 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6102. Min Act: -0.1700
Data Index: 3700940 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6972. Min Range: -1.6972
Max Act: 1.6190. Min Act: -0.1700
Data Index: 7365951 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19