Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6312 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2966. Min Range: -7.2966
Max Act: 7.2653. Min Act: -0.1700
Data Index: 4654685 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2966. Min Range: -7.2966
Max Act: 7.2966. Min Act: -0.1700
Data Index: 6126761 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2966. Min Range: -7.2966
Max Act: 7.1716. Min Act: -0.1700
Data Index: 3282819 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2966. Min Range: -7.2966
Max Act: 7.1091. Min Act: -0.1700
Data Index: 2811291 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2966. Min Range: -7.2966
Max Act: 7.1091. Min Act: -0.1700
Data Index: 976584 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2966. Min Range: -7.2966
Max Act: 7.1091. Min Act: -0.1700
Data Index: 757015 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2966. Min Range: -7.2966
Max Act: 7.0153. Min Act: -0.1700
Data Index: 790234 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2966. Min Range: -7.2966
Max Act: 6.8903. Min Act: -0.1700
Data Index: 3282817 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2966. Min Range: -7.2966
Max Act: 6.8278. Min Act: -0.1700
Data Index: 5472536 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2966. Min Range: -7.2966
Max Act: 6.8278. Min Act: -0.1700
Data Index: 3879730 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2966. Min Range: -7.2966
Max Act: 6.7653. Min Act: -0.1700
Data Index: 672622 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2966. Min Range: -7.2966
Max Act: 6.7966. Min Act: -0.1700
Data Index: 1177354 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2966. Min Range: -7.2966
Max Act: 6.7966. Min Act: -0.1700
Data Index: 5645428 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2966. Min Range: -7.2966
Max Act: 6.7653. Min Act: -0.1700
Data Index: 2820945 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2966. Min Range: -7.2966
Max Act: 6.7966. Min Act: -0.1700
Data Index: 73608 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2966. Min Range: -7.2966
Max Act: 6.7653. Min Act: -0.1700
Data Index: 1947553 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2966. Min Range: -7.2966
Max Act: 6.7653. Min Act: -0.1700
Data Index: 7845188 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2966. Min Range: -7.2966
Max Act: 6.7653. Min Act: -0.1700
Data Index: 6530998 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2966. Min Range: -7.2966
Max Act: 6.7653. Min Act: -0.1700
Data Index: 3695181 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2966. Min Range: -7.2966
Max Act: 6.6716. Min Act: -0.1700
Data Index: 2488950 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19