Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3043 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0592. Min Range: -7.0592
Max Act: 7.0592. Min Act: -0.1700
Data Index: 5484413 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.8717. Min Act: -0.1700
Data Index: 5294690 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.8092. Min Act: -0.1700
Data Index: 3566055 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.8405. Min Act: -0.1700
Data Index: 5278899 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.8092. Min Act: -0.1700
Data Index: 3135941 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.7780. Min Act: -0.1700
Data Index: 4827477 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.5905. Min Act: -0.1700
Data Index: 5226198 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.6217. Min Act: -0.1700
Data Index: 60287 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.5905. Min Act: -0.1700
Data Index: 1029971 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.6217. Min Act: -0.1700
Data Index: 329869 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.5592. Min Act: -0.1700
Data Index: 1814993 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.5280. Min Act: -0.1700
Data Index: 3391801 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.4655. Min Act: -0.1700
Data Index: 326187 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.4655. Min Act: -0.1700
Data Index: 3962471 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.4655. Min Act: -0.1700
Data Index: 6888829 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.4655. Min Act: -0.1700
Data Index: 7888386 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.4342. Min Act: -0.1700
Data Index: 770852 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.4342. Min Act: -0.1700
Data Index: 5713191 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.4030. Min Act: -0.1700
Data Index: 3980604 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0592. Min Range: -7.0592
Max Act: 6.4030. Min Act: -0.1700
Data Index: 5096377 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19