Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2594 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4332. Min Range: -7.4332
Max Act: 7.4332. Min Act: -0.1700
Data Index: 4656023 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4332. Min Range: -7.4332
Max Act: 7.3394. Min Act: -0.1700
Data Index: 7925511 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4332. Min Range: -7.4332
Max Act: 7.1519. Min Act: -0.1700
Data Index: 5105777 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4332. Min Range: -7.4332
Max Act: 7.0269. Min Act: -0.1700
Data Index: 1829072 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.8082. Min Act: -0.1700
Data Index: 8271696 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.6832. Min Act: -0.1700
Data Index: 1359063 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.6207. Min Act: -0.1700
Data Index: 7093772 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.5894. Min Act: -0.1700
Data Index: 158397 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.5894. Min Act: -0.1700
Data Index: 2609618 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.5894. Min Act: -0.1700
Data Index: 7826707 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.4957. Min Act: -0.1700
Data Index: 6815242 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.5269. Min Act: -0.1700
Data Index: 859360 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.4957. Min Act: -0.1700
Data Index: 6331111 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.4644. Min Act: -0.1700
Data Index: 2143169 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.4644. Min Act: -0.1700
Data Index: 7959582 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.4644. Min Act: -0.1700
Data Index: 6240061 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.4332. Min Act: -0.1700
Data Index: 5378619 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.4332. Min Act: -0.1700
Data Index: 7863104 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.4332. Min Act: -0.1700
Data Index: 6272300 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4332. Min Range: -7.4332
Max Act: 6.4019. Min Act: -0.1700
Data Index: 1079810 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19