Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 773 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4962. Min Act: -0.1700
Data Index: 4358466 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4649. Min Act: -0.1700
Data Index: 4358463 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4337. Min Act: -0.1700
Data Index: 6938829 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4337. Min Act: -0.1700
Data Index: 927952 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4337. Min Act: -0.1700
Data Index: 2148440 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4649. Min Act: -0.1700
Data Index: 6938832 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4337. Min Act: -0.1700
Data Index: 6938833 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4337. Min Act: -0.1700
Data Index: 210005 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4024. Min Act: -0.1700
Data Index: 210003 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4024. Min Act: -0.1700
Data Index: 6938828 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4024. Min Act: -0.1700
Data Index: 2820309 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4024. Min Act: -0.1700
Data Index: 2148441 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4024. Min Act: -0.1700
Data Index: 2148437 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4024. Min Act: -0.1700
Data Index: 2148438 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4024. Min Act: -0.1700
Data Index: 4358476 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4024. Min Act: -0.1700
Data Index: 927953 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.3712. Min Act: -0.1700
Data Index: 2820303 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.4024. Min Act: -0.1700
Data Index: 4358470 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.3399. Min Act: -0.1700
Data Index: 4358465 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4962. Min Range: -4.4962
Max Act: 4.3712. Min Act: -0.1700
Data Index: 2820305 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19