Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2966 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.2515. Min Act: -0.1700
Data Index: 757143 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.1890. Min Act: -0.1700
Data Index: 1115375 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.1890. Min Act: -0.1700
Data Index: 1033899 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.1890. Min Act: -0.1700
Data Index: 1139450 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.1577. Min Act: -0.1700
Data Index: 423556 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.1577. Min Act: -0.1700
Data Index: 2997131 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.1577. Min Act: -0.1700
Data Index: 535404 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.1577. Min Act: -0.1700
Data Index: 7192193 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.1577. Min Act: -0.1700
Data Index: 5604390 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.1265. Min Act: -0.1700
Data Index: 3127079 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.1577. Min Act: -0.1700
Data Index: 843744 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.1265. Min Act: -0.1700
Data Index: 503977 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.0952. Min Act: -0.1700
Data Index: 4628211 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.0952. Min Act: -0.1700
Data Index: 4484266 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.0952. Min Act: -0.1700
Data Index: 949532 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.0952. Min Act: -0.1700
Data Index: 949531 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.0327. Min Act: -0.1700
Data Index: 4676633 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.0327. Min Act: -0.1700
Data Index: 2320826 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.0327. Min Act: -0.1700
Data Index: 2618760 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2515. Min Range: -5.2515
Max Act: 5.0327. Min Act: -0.1700
Data Index: 6449532 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19