Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0437. Min Range: -5.0437
Max Act: 5.0437. Min Act: -0.1700
Data Index: 8526488 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0437. Min Range: -5.0437
Max Act: 5.0124. Min Act: -0.1700
Data Index: 3207898 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.9499. Min Act: -0.1700
Data Index: 728905 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.9812. Min Act: -0.1700
Data Index: 8824667 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.9812. Min Act: -0.1700
Data Index: 7032519 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.9187. Min Act: -0.1700
Data Index: 723702 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.9187. Min Act: -0.1700
Data Index: 2273017 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.9499. Min Act: -0.1700
Data Index: 5217816 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.9187. Min Act: -0.1700
Data Index: 6128152 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.8562. Min Act: -0.1700
Data Index: 1520283 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.8249. Min Act: -0.1700
Data Index: 693464 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.8249. Min Act: -0.1700
Data Index: 1164690 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.8249. Min Act: -0.1700
Data Index: 295510 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.8249. Min Act: -0.1700
Data Index: 4204195 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.8249. Min Act: -0.1700
Data Index: 7959710 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.8249. Min Act: -0.1700
Data Index: 3348583 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.8249. Min Act: -0.1700
Data Index: 6273447 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.8249. Min Act: -0.1700
Data Index: 4862298 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.8249. Min Act: -0.1700
Data Index: 2546795 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0437. Min Range: -5.0437
Max Act: 4.7937. Min Act: -0.1700
Data Index: 368648 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19