Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4163 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.8451. Min Act: -0.1700
Data Index: 6574064 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.8138. Min Act: -0.1700
Data Index: 2338382 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.8138. Min Act: -0.1700
Data Index: 72401 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.7513. Min Act: -0.1700
Data Index: 7218236 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.7201. Min Act: -0.1700
Data Index: 136972 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.7513. Min Act: -0.1700
Data Index: 1203623 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.6888. Min Act: -0.1700
Data Index: 4145831 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.7201. Min Act: -0.1700
Data Index: 8703535 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.7201. Min Act: -0.1700
Data Index: 5493793 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.6888. Min Act: -0.1700
Data Index: 2419831 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.6576. Min Act: -0.1700
Data Index: 649869 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.6888. Min Act: -0.1700
Data Index: 4207680 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.6888. Min Act: -0.1700
Data Index: 6739177 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.6576. Min Act: -0.1700
Data Index: 4873527 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.6263. Min Act: -0.1700
Data Index: 3966636 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.6263. Min Act: -0.1700
Data Index: 4907719 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.6263. Min Act: -0.1700
Data Index: 3406084 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.6263. Min Act: -0.1700
Data Index: 4481711 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.6263. Min Act: -0.1700
Data Index: 1657654 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8451. Min Range: -4.8451
Max Act: 4.6263. Min Act: -0.1700
Data Index: 3912731 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19