Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1550. Min Range: -5.1550
Max Act: 5.1550. Min Act: -0.1700
Data Index: 432857 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1550. Min Range: -5.1550
Max Act: 5.1550. Min Act: -0.1700
Data Index: 8070161 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1550. Min Range: -5.1550
Max Act: 5.1550. Min Act: -0.1700
Data Index: 2836052 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1550. Min Range: -5.1550
Max Act: 5.0925. Min Act: -0.1700
Data Index: 614650 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1550. Min Range: -5.1550
Max Act: 5.0613. Min Act: -0.1700
Data Index: 6848325 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1550. Min Range: -5.1550
Max Act: 5.0613. Min Act: -0.1700
Data Index: 8269662 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1550. Min Range: -5.1550
Max Act: 5.0613. Min Act: -0.1700
Data Index: 737381 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1550. Min Range: -5.1550
Max Act: 4.9675. Min Act: -0.1700
Data Index: 5400986 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1550. Min Range: -5.1550
Max Act: 4.9675. Min Act: -0.1700
Data Index: 776820 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1550. Min Range: -5.1550
Max Act: 4.9675. Min Act: -0.1700
Data Index: 4246196 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1550. Min Range: -5.1550
Max Act: 4.9988. Min Act: -0.1700
Data Index: 1219535 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1550. Min Range: -5.1550
Max Act: 4.9675. Min Act: -0.1700
Data Index: 3440004 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1550. Min Range: -5.1550
Max Act: 4.9675. Min Act: -0.1700
Data Index: 796928 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1550. Min Range: -5.1550
Max Act: 4.9675. Min Act: -0.1700
Data Index: 6506394 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1550. Min Range: -5.1550
Max Act: 4.9363. Min Act: -0.1700
Data Index: 4182050 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1550. Min Range: -5.1550
Max Act: 4.9363. Min Act: -0.1700
Data Index: 774254 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1550. Min Range: -5.1550
Max Act: 4.9363. Min Act: -0.1700
Data Index: 5756780 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1550. Min Range: -5.1550
Max Act: 4.9050. Min Act: -0.1700
Data Index: 920207 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1550. Min Range: -5.1550
Max Act: 4.9050. Min Act: -0.1700
Data Index: 4979627 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1550. Min Range: -5.1550
Max Act: 4.9050. Min Act: -0.1700
Data Index: 5356113 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19