Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6385 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4983. Min Range: -9.4983
Max Act: 9.4983. Min Act: -0.1700
Data Index: 6382033 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4983. Min Range: -9.4983
Max Act: 9.4358. Min Act: -0.1700
Data Index: 2610820 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4983. Min Range: -9.4983
Max Act: 9.4358. Min Act: -0.1700
Data Index: 23481 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4983. Min Range: -9.4983
Max Act: 9.3108. Min Act: -0.1700
Data Index: 1286839 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4983. Min Range: -9.4983
Max Act: 9.3733. Min Act: -0.1700
Data Index: 1656155 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4983. Min Range: -9.4983
Max Act: 9.1858. Min Act: -0.1700
Data Index: 7277091 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4983. Min Range: -9.4983
Max Act: 9.1858. Min Act: -0.1700
Data Index: 5223366 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4983. Min Range: -9.4983
Max Act: 9.1233. Min Act: -0.1700
Data Index: 4392231 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4983. Min Range: -9.4983
Max Act: 9.1233. Min Act: -0.1700
Data Index: 1498641 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4983. Min Range: -9.4983
Max Act: 8.9983. Min Act: -0.1700
Data Index: 6556798 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4983. Min Range: -9.4983
Max Act: 8.9983. Min Act: -0.1700
Data Index: 325570 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4983. Min Range: -9.4983
Max Act: 8.9983. Min Act: -0.1700
Data Index: 1512484 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4983. Min Range: -9.4983
Max Act: 8.9983. Min Act: -0.1700
Data Index: 5023072 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4983. Min Range: -9.4983
Max Act: 8.9358. Min Act: -0.1700
Data Index: 7869649 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4983. Min Range: -9.4983
Max Act: 8.9358. Min Act: -0.1700
Data Index: 5223365 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4983. Min Range: -9.4983
Max Act: 8.9358. Min Act: -0.1700
Data Index: 5191024 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4983. Min Range: -9.4983
Max Act: 8.9358. Min Act: -0.1700
Data Index: 499448 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4983. Min Range: -9.4983
Max Act: 8.8733. Min Act: -0.1700
Data Index: 8328447 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4983. Min Range: -9.4983
Max Act: 8.8733. Min Act: -0.1700
Data Index: 2820542 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4983. Min Range: -9.4983
Max Act: 8.8733. Min Act: -0.1700
Data Index: 7453398 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19