Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5326. Min Range: -7.5326
Max Act: 7.5326. Min Act: -0.1700
Data Index: 5142569 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5326. Min Range: -7.5326
Max Act: 7.3451. Min Act: -0.1700
Data Index: 712552 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5326. Min Range: -7.5326
Max Act: 7.3138. Min Act: -0.1700
Data Index: 1472103 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5326. Min Range: -7.5326
Max Act: 7.2513. Min Act: -0.1700
Data Index: 4124862 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5326. Min Range: -7.5326
Max Act: 7.1888. Min Act: -0.1700
Data Index: 5728546 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5326. Min Range: -7.5326
Max Act: 7.1576. Min Act: -0.1700
Data Index: 2933035 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5326. Min Range: -7.5326
Max Act: 7.1576. Min Act: -0.1700
Data Index: 500 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5326. Min Range: -7.5326
Max Act: 7.0638. Min Act: -0.1700
Data Index: 4560635 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5326. Min Range: -7.5326
Max Act: 7.0638. Min Act: -0.1700
Data Index: 6025239 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5326. Min Range: -7.5326
Max Act: 7.0326. Min Act: -0.1700
Data Index: 6783701 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5326. Min Range: -7.5326
Max Act: 7.0013. Min Act: -0.1700
Data Index: 3263133 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5326. Min Range: -7.5326
Max Act: 6.9701. Min Act: -0.1700
Data Index: 1512225 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5326. Min Range: -7.5326
Max Act: 6.9701. Min Act: -0.1700
Data Index: 2543964 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5326. Min Range: -7.5326
Max Act: 6.9701. Min Act: -0.1700
Data Index: 6368062 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5326. Min Range: -7.5326
Max Act: 6.9388. Min Act: -0.1700
Data Index: 280896 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5326. Min Range: -7.5326
Max Act: 6.9388. Min Act: -0.1700
Data Index: 4599153 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5326. Min Range: -7.5326
Max Act: 6.9388. Min Act: -0.1700
Data Index: 8708850 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5326. Min Range: -7.5326
Max Act: 6.8763. Min Act: -0.1700
Data Index: 2442094 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5326. Min Range: -7.5326
Max Act: 6.9076. Min Act: -0.1700
Data Index: 1496691 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5326. Min Range: -7.5326
Max Act: 6.9076. Min Act: -0.1700
Data Index: 5723711 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19