Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3449 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.6775. Min Act: -0.1700
Data Index: 6567075 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.6150. Min Act: -0.1700
Data Index: 623386 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.5837. Min Act: -0.1700
Data Index: 6892241 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.5525. Min Act: -0.1700
Data Index: 6543646 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.5525. Min Act: -0.1700
Data Index: 4608280 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.5525. Min Act: -0.1700
Data Index: 5852069 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.5837. Min Act: -0.1700
Data Index: 6476368 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.5212. Min Act: -0.1700
Data Index: 1014846 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.5212. Min Act: -0.1700
Data Index: 6409492 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.5212. Min Act: -0.1700
Data Index: 8508457 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.5525. Min Act: -0.1700
Data Index: 7678397 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.5212. Min Act: -0.1700
Data Index: 6980216 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.4900. Min Act: -0.1700
Data Index: 1182505 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.4900. Min Act: -0.1700
Data Index: 26834 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.4900. Min Act: -0.1700
Data Index: 5209008 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.4900. Min Act: -0.1700
Data Index: 5783800 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.4587. Min Act: -0.1700
Data Index: 7741757 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.5212. Min Act: -0.1700
Data Index: 3481809 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.4587. Min Act: -0.1700
Data Index: 5529924 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6775. Min Range: -4.6775
Max Act: 4.4587. Min Act: -0.1700
Data Index: 1092489 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19