Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 415 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7768. Min Range: -9.7768
Max Act: 9.7768. Min Act: -0.1700
Data Index: 2162222 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7768. Min Range: -9.7768
Max Act: 9.2143. Min Act: -0.1700
Data Index: 996548 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7768. Min Range: -9.7768
Max Act: 9.0893. Min Act: -0.1700
Data Index: 3585533 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7768. Min Range: -9.7768
Max Act: 9.0893. Min Act: -0.1700
Data Index: 1500806 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7768. Min Range: -9.7768
Max Act: 9.0893. Min Act: -0.1700
Data Index: 6173708 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7768. Min Range: -9.7768
Max Act: 8.9643. Min Act: -0.1700
Data Index: 6611527 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7768. Min Range: -9.7768
Max Act: 8.9018. Min Act: -0.1700
Data Index: 1529128 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7768. Min Range: -9.7768
Max Act: 8.8393. Min Act: -0.1700
Data Index: 8448180 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7768. Min Range: -9.7768
Max Act: 8.8393. Min Act: -0.1700
Data Index: 814849 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7768. Min Range: -9.7768
Max Act: 8.8393. Min Act: -0.1700
Data Index: 5990664 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7768. Min Range: -9.7768
Max Act: 8.8393. Min Act: -0.1700
Data Index: 5771735 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7768. Min Range: -9.7768
Max Act: 8.8393. Min Act: -0.1700
Data Index: 5611199 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7768. Min Range: -9.7768
Max Act: 8.8393. Min Act: -0.1700
Data Index: 8713614 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7768. Min Range: -9.7768
Max Act: 8.8393. Min Act: -0.1700
Data Index: 8664080 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7768. Min Range: -9.7768
Max Act: 8.8393. Min Act: -0.1700
Data Index: 8044923 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7768. Min Range: -9.7768
Max Act: 8.7768. Min Act: -0.1700
Data Index: 4068273 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7768. Min Range: -9.7768
Max Act: 8.7768. Min Act: -0.1700
Data Index: 4142710 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7768. Min Range: -9.7768
Max Act: 8.7768. Min Act: -0.1700
Data Index: 6653446 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7768. Min Range: -9.7768
Max Act: 8.7768. Min Act: -0.1700
Data Index: 4401221 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7768. Min Range: -9.7768
Max Act: 8.7143. Min Act: -0.1700
Data Index: 7383796 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19