Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5759 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0968. Min Range: -6.0968
Max Act: 6.0968. Min Act: -0.1700
Data Index: 6325400 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0968. Min Range: -6.0968
Max Act: 6.0655. Min Act: -0.1700
Data Index: 2673867 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0968. Min Range: -6.0968
Max Act: 6.0030. Min Act: -0.1700
Data Index: 8156884 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.9718. Min Act: -0.1700
Data Index: 662995 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.9093. Min Act: -0.1700
Data Index: 1984205 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.8468. Min Act: -0.1700
Data Index: 4134113 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.7843. Min Act: -0.1700
Data Index: 6041817 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.7843. Min Act: -0.1700
Data Index: 2332975 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.7843. Min Act: -0.1700
Data Index: 880295 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.7843. Min Act: -0.1700
Data Index: 675560 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.7218. Min Act: -0.1700
Data Index: 2656664 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.7530. Min Act: -0.1700
Data Index: 8397112 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.7218. Min Act: -0.1700
Data Index: 3905454 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.7218. Min Act: -0.1700
Data Index: 5094765 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.7218. Min Act: -0.1700
Data Index: 4313231 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.7218. Min Act: -0.1700
Data Index: 2074531 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.6905. Min Act: -0.1700
Data Index: 8271389 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.6905. Min Act: -0.1700
Data Index: 1018189 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.6905. Min Act: -0.1700
Data Index: 2843857 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0968. Min Range: -6.0968
Max Act: 5.6905. Min Act: -0.1700
Data Index: 5270703 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19