Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2944 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.5935. Min Act: -0.1700
Data Index: 2848050 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.4060. Min Act: -0.1700
Data Index: 2931629 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.3435. Min Act: -0.1700
Data Index: 2837692 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.2810. Min Act: -0.1700
Data Index: 6761624 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.2810. Min Act: -0.1700
Data Index: 437050 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.2497. Min Act: -0.1700
Data Index: 757277 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.2185. Min Act: -0.1700
Data Index: 1797286 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.1872. Min Act: -0.1700
Data Index: 8316 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.1560. Min Act: -0.1700
Data Index: 7904277 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.1560. Min Act: -0.1700
Data Index: 351344 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.1560. Min Act: -0.1700
Data Index: 8131207 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.1247. Min Act: -0.1700
Data Index: 3172374 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.0935. Min Act: -0.1700
Data Index: 3311234 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.0935. Min Act: -0.1700
Data Index: 8511765 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.0935. Min Act: -0.1700
Data Index: 1435627 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.0935. Min Act: -0.1700
Data Index: 3823089 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.0622. Min Act: -0.1700
Data Index: 7335490 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.0622. Min Act: -0.1700
Data Index: 1492373 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5935. Min Range: -6.5935
Max Act: 6.0310. Min Act: -0.1700
Data Index: 8053575 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5935. Min Range: -6.5935
Max Act: 5.9997. Min Act: -0.1700
Data Index: 2291410 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19