Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4940 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.8480. Min Act: -0.1700
Data Index: 5677405 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.8480. Min Act: -0.1700
Data Index: 6967549 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.7543. Min Act: -0.1700
Data Index: 617418 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.5668. Min Act: -0.1700
Data Index: 4505025 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.5668. Min Act: -0.1700
Data Index: 127375 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.5043. Min Act: -0.1700
Data Index: 4667641 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.5043. Min Act: -0.1700
Data Index: 5677406 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.5043. Min Act: -0.1700
Data Index: 7708022 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.4730. Min Act: -0.1700
Data Index: 8824093 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.4418. Min Act: -0.1700
Data Index: 5185969 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.4730. Min Act: -0.1700
Data Index: 5940696 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.4418. Min Act: -0.1700
Data Index: 848351 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.4418. Min Act: -0.1700
Data Index: 8157639 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.4105. Min Act: -0.1700
Data Index: 182587 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.4105. Min Act: -0.1700
Data Index: 5466141 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.3793. Min Act: -0.1700
Data Index: 7251943 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.3480. Min Act: -0.1700
Data Index: 8519356 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.3480. Min Act: -0.1700
Data Index: 7352438 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.3480. Min Act: -0.1700
Data Index: 5883897 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8480. Min Range: -5.8480
Max Act: 5.3793. Min Act: -0.1700
Data Index: 2010857 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19