Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5106 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.5020. Min Act: -0.1700
Data Index: 1078376 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.3457. Min Act: -0.1700
Data Index: 5078989 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.2832. Min Act: -0.1700
Data Index: 8028381 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.2520. Min Act: -0.1700
Data Index: 2648563 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.2520. Min Act: -0.1700
Data Index: 7514095 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.2207. Min Act: -0.1700
Data Index: 5435196 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.1582. Min Act: -0.1700
Data Index: 4150307 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.1270. Min Act: -0.1700
Data Index: 325533 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.1582. Min Act: -0.1700
Data Index: 3088545 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.1582. Min Act: -0.1700
Data Index: 7532042 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.1270. Min Act: -0.1700
Data Index: 8425276 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.1582. Min Act: -0.1700
Data Index: 3530846 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.0957. Min Act: -0.1700
Data Index: 7704521 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.1270. Min Act: -0.1700
Data Index: 6152225 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.0957. Min Act: -0.1700
Data Index: 6628145 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.0957. Min Act: -0.1700
Data Index: 1449286 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.0645. Min Act: -0.1700
Data Index: 2351806 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.0957. Min Act: -0.1700
Data Index: 477821 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.0957. Min Act: -0.1700
Data Index: 6860382 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5020. Min Range: -5.5020
Max Act: 5.0957. Min Act: -0.1700
Data Index: 4306003 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19