Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 38 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0252. Min Range: -5.0252
Max Act: 5.0252. Min Act: -0.1700
Data Index: 2739217 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.9627. Min Act: -0.1700
Data Index: 2889437 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.9627. Min Act: -0.1700
Data Index: 4589353 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.9315. Min Act: -0.1700
Data Index: 308054 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.9002. Min Act: -0.1700
Data Index: 8779276 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.9002. Min Act: -0.1700
Data Index: 7960691 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.9002. Min Act: -0.1700
Data Index: 7925081 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.8690. Min Act: -0.1700
Data Index: 7282385 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.8377. Min Act: -0.1700
Data Index: 6436046 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.8065. Min Act: -0.1700
Data Index: 2003664 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.8065. Min Act: -0.1700
Data Index: 4901628 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.8065. Min Act: -0.1700
Data Index: 7982748 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.8065. Min Act: -0.1700
Data Index: 617121 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.8065. Min Act: -0.1700
Data Index: 3379350 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.8065. Min Act: -0.1700
Data Index: 8048192 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.7752. Min Act: -0.1700
Data Index: 3895511 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.7752. Min Act: -0.1700
Data Index: 1210058 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.7752. Min Act: -0.1700
Data Index: 468071 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.7752. Min Act: -0.1700
Data Index: 269370 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0252. Min Range: -5.0252
Max Act: 4.7752. Min Act: -0.1700
Data Index: 8527782 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19