Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1485 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.6087. Min Act: -0.1700
Data Index: 1211439 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.5149. Min Act: -0.1700
Data Index: 3575598 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.3899. Min Act: -0.1700
Data Index: 2937303 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.3899. Min Act: -0.1700
Data Index: 6930367 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.3587. Min Act: -0.1700
Data Index: 828942 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.3587. Min Act: -0.1700
Data Index: 1087216 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.2649. Min Act: -0.1700
Data Index: 5140552 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.2337. Min Act: -0.1700
Data Index: 5593698 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.2024. Min Act: -0.1700
Data Index: 2629685 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.1712. Min Act: -0.1700
Data Index: 8172375 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.1712. Min Act: -0.1700
Data Index: 1031110 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.1712. Min Act: -0.1700
Data Index: 4235439 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.1712. Min Act: -0.1700
Data Index: 1873133 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.1712. Min Act: -0.1700
Data Index: 5202812 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.1399. Min Act: -0.1700
Data Index: 4015082 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.1399. Min Act: -0.1700
Data Index: 6523227 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.1399. Min Act: -0.1700
Data Index: 4715654 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.1399. Min Act: -0.1700
Data Index: 6417488 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.1399. Min Act: -0.1700
Data Index: 5656770 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6087. Min Range: -5.6087
Max Act: 5.1087. Min Act: -0.1700
Data Index: 2393968 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19