Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4313 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.6276. Min Act: -0.1700
Data Index: 8362905 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.4088. Min Act: -0.1700
Data Index: 3811211 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.3463. Min Act: -0.1700
Data Index: 8033575 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.3463. Min Act: -0.1700
Data Index: 3489324 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.3151. Min Act: -0.1700
Data Index: 3567070 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.2838. Min Act: -0.1700
Data Index: 5091895 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.2526. Min Act: -0.1700
Data Index: 4818413 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.2526. Min Act: -0.1700
Data Index: 2229733 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.2213. Min Act: -0.1700
Data Index: 7166369 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.2213. Min Act: -0.1700
Data Index: 7588549 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.2213. Min Act: -0.1700
Data Index: 5644130 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.1901. Min Act: -0.1700
Data Index: 748002 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.1588. Min Act: -0.1700
Data Index: 781118 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.1588. Min Act: -0.1700
Data Index: 4385585 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.1901. Min Act: -0.1700
Data Index: 5597380 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.1276. Min Act: -0.1700
Data Index: 7645447 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.1588. Min Act: -0.1700
Data Index: 5759740 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.1276. Min Act: -0.1700
Data Index: 674638 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.1276. Min Act: -0.1700
Data Index: 967818 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6276. Min Range: -6.6276
Max Act: 6.0963. Min Act: -0.1700
Data Index: 7832244 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19