Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2438 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1966. Min Range: -8.1966
Max Act: 8.1966. Min Act: -0.1700
Data Index: 5957489 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1966. Min Range: -8.1966
Max Act: 8.1654. Min Act: -0.1700
Data Index: 1755801 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1966. Min Range: -8.1966
Max Act: 8.1341. Min Act: -0.1700
Data Index: 6761017 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1966. Min Range: -8.1966
Max Act: 8.0091. Min Act: -0.1700
Data Index: 4456789 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1966. Min Range: -8.1966
Max Act: 8.0404. Min Act: -0.1700
Data Index: 7925332 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1966. Min Range: -8.1966
Max Act: 7.9466. Min Act: -0.1700
Data Index: 8129190 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1966. Min Range: -8.1966
Max Act: 7.9466. Min Act: -0.1700
Data Index: 5018348 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1966. Min Range: -8.1966
Max Act: 7.8841. Min Act: -0.1700
Data Index: 4453705 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1966. Min Range: -8.1966
Max Act: 7.7591. Min Act: -0.1700
Data Index: 8820134 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1966. Min Range: -8.1966
Max Act: 7.7591. Min Act: -0.1700
Data Index: 5598461 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1966. Min Range: -8.1966
Max Act: 7.7591. Min Act: -0.1700
Data Index: 633359 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1966. Min Range: -8.1966
Max Act: 7.7279. Min Act: -0.1700
Data Index: 926774 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1966. Min Range: -8.1966
Max Act: 7.6966. Min Act: -0.1700
Data Index: 4839260 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1966. Min Range: -8.1966
Max Act: 7.6966. Min Act: -0.1700
Data Index: 26023 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1966. Min Range: -8.1966
Max Act: 7.6966. Min Act: -0.1700
Data Index: 616828 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1966. Min Range: -8.1966
Max Act: 7.6966. Min Act: -0.1700
Data Index: 7226502 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1966. Min Range: -8.1966
Max Act: 7.6341. Min Act: -0.1700
Data Index: 5631252 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1966. Min Range: -8.1966
Max Act: 7.6341. Min Act: -0.1700
Data Index: 301019 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1966. Min Range: -8.1966
Max Act: 7.6029. Min Act: -0.1700
Data Index: 3651699 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1966. Min Range: -8.1966
Max Act: 7.6029. Min Act: -0.1700
Data Index: 5732593 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19