Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5494 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1469. Min Range: -6.1469
Max Act: 6.1469. Min Act: -0.1700
Data Index: 726432 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1469. Min Range: -6.1469
Max Act: 6.0532. Min Act: -0.1700
Data Index: 97590 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1469. Min Range: -6.1469
Max Act: 6.0219. Min Act: -0.1700
Data Index: 4375059 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1469. Min Range: -6.1469
Max Act: 6.0219. Min Act: -0.1700
Data Index: 6640247 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1469. Min Range: -6.1469
Max Act: 5.9907. Min Act: -0.1700
Data Index: 606460 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1469. Min Range: -6.1469
Max Act: 6.0219. Min Act: -0.1700
Data Index: 8471796 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1469. Min Range: -6.1469
Max Act: 5.9907. Min Act: -0.1700
Data Index: 4268163 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1469. Min Range: -6.1469
Max Act: 5.9282. Min Act: -0.1700
Data Index: 6894300 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1469. Min Range: -6.1469
Max Act: 5.9282. Min Act: -0.1700
Data Index: 8719018 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1469. Min Range: -6.1469
Max Act: 5.8969. Min Act: -0.1700
Data Index: 3162104 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1469. Min Range: -6.1469
Max Act: 5.8969. Min Act: -0.1700
Data Index: 6026703 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1469. Min Range: -6.1469
Max Act: 5.8969. Min Act: -0.1700
Data Index: 7879410 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1469. Min Range: -6.1469
Max Act: 5.8969. Min Act: -0.1700
Data Index: 3045572 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1469. Min Range: -6.1469
Max Act: 5.8969. Min Act: -0.1700
Data Index: 908582 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1469. Min Range: -6.1469
Max Act: 5.8657. Min Act: -0.1700
Data Index: 2529497 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1469. Min Range: -6.1469
Max Act: 5.8657. Min Act: -0.1700
Data Index: 2182863 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1469. Min Range: -6.1469
Max Act: 5.8344. Min Act: -0.1700
Data Index: 784816 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1469. Min Range: -6.1469
Max Act: 5.8032. Min Act: -0.1700
Data Index: 5590271 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1469. Min Range: -6.1469
Max Act: 5.7719. Min Act: -0.1700
Data Index: 7020252 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1469. Min Range: -6.1469
Max Act: 5.7719. Min Act: -0.1700
Data Index: 5380663 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19