Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5470 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.9807. Min Act: -0.1700
Data Index: 7169615 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.8557. Min Act: -0.1700
Data Index: 185783 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.8557. Min Act: -0.1700
Data Index: 1160303 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.8557. Min Act: -0.1700
Data Index: 7684087 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.7932. Min Act: -0.1700
Data Index: 2246735 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.7307. Min Act: -0.1700
Data Index: 1423494 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.6682. Min Act: -0.1700
Data Index: 6236738 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.6682. Min Act: -0.1700
Data Index: 8048001 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.6682. Min Act: -0.1700
Data Index: 4700434 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.6682. Min Act: -0.1700
Data Index: 3628088 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.6057. Min Act: -0.1700
Data Index: 6106862 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.5432. Min Act: -0.1700
Data Index: 7339142 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.6057. Min Act: -0.1700
Data Index: 2699332 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.6057. Min Act: -0.1700
Data Index: 7517137 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.5432. Min Act: -0.1700
Data Index: 3888527 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.4182. Min Act: -0.1700
Data Index: 5083756 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.4182. Min Act: -0.1700
Data Index: 673176 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.4807. Min Act: -0.1700
Data Index: 3886905 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.4807. Min Act: -0.1700
Data Index: 1075180 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9807. Min Range: -9.9807
Max Act: 9.4807. Min Act: -0.1700
Data Index: 1170718 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19