Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2838 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.5543. Min Act: -0.1700
Data Index: 634604 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.5543. Min Act: -0.1700
Data Index: 3918427 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.4918. Min Act: -0.1700
Data Index: 6635870 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.4606. Min Act: -0.1700
Data Index: 8693394 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.3668. Min Act: -0.1700
Data Index: 4968963 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.3356. Min Act: -0.1700
Data Index: 7279870 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.3356. Min Act: -0.1700
Data Index: 6720367 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.2418. Min Act: -0.1700
Data Index: 4851358 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.2418. Min Act: -0.1700
Data Index: 4330175 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.2418. Min Act: -0.1700
Data Index: 5881181 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.2418. Min Act: -0.1700
Data Index: 7158463 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.2106. Min Act: -0.1700
Data Index: 4731066 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.1793. Min Act: -0.1700
Data Index: 7521544 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.2106. Min Act: -0.1700
Data Index: 7860473 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.2106. Min Act: -0.1700
Data Index: 1361188 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.2106. Min Act: -0.1700
Data Index: 4697477 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.1793. Min Act: -0.1700
Data Index: 2436674 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.1481. Min Act: -0.1700
Data Index: 206493 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.1481. Min Act: -0.1700
Data Index: 1695318 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5543. Min Range: -6.5543
Max Act: 6.1168. Min Act: -0.1700
Data Index: 2099355 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19