Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 900 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.6433. Min Act: -0.1699
Data Index: 1572973 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.6036. Min Act: -0.1698
Data Index: 5430494 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.5261. Min Act: -0.1699
Data Index: 4356086 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.5109. Min Act: -0.1700
Data Index: 3196405 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.5185. Min Act: -0.1700
Data Index: 841530 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.5109. Min Act: -0.1700
Data Index: 3737764 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.5185. Min Act: -0.1698
Data Index: 7528280 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.5109. Min Act: -0.1688
Data Index: 2590154 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.5034. Min Act: -0.1700
Data Index: 8805560 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.5034. Min Act: -0.1676
Data Index: 786090 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.5109. Min Act: -0.1695
Data Index: 5695647 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.5034. Min Act: -0.1700
Data Index: 2233778 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.4959. Min Act: -0.1698
Data Index: 8179272 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.4959. Min Act: -0.1699
Data Index: 7643816 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.4884. Min Act: -0.1693
Data Index: 6580812 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.4810. Min Act: -0.1700
Data Index: 6723318 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.4884. Min Act: -0.1700
Data Index: 3330248 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.4810. Min Act: -0.1699
Data Index: 7274592 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.4810. Min Act: -0.1699
Data Index: 1866882 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6433. Min Range: -0.6433
Max Act: 0.4810. Min Act: -0.1700
Data Index: 4445682 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19