Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3595 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.9050. Min Act: -0.1700
Data Index: 1485139 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.9050. Min Act: -0.1700
Data Index: 4490535 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.5925. Min Act: -0.1700
Data Index: 8091448 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.5613. Min Act: -0.1700
Data Index: 327716 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.4988. Min Act: -0.1700
Data Index: 5754933 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.4988. Min Act: -0.1700
Data Index: 2864450 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.4363. Min Act: -0.1700
Data Index: 1910527 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.3738. Min Act: -0.1700
Data Index: 3873981 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.4050. Min Act: -0.1700
Data Index: 349844 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.4050. Min Act: -0.1700
Data Index: 7706089 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.3738. Min Act: -0.1700
Data Index: 519141 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.3738. Min Act: -0.1700
Data Index: 2351933 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.3738. Min Act: -0.1700
Data Index: 3278892 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.4050. Min Act: -0.1700
Data Index: 8471878 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.3425. Min Act: -0.1700
Data Index: 8309546 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.3113. Min Act: -0.1700
Data Index: 1380287 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.3113. Min Act: -0.1700
Data Index: 4837622 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.3113. Min Act: -0.1700
Data Index: 5669934 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.3113. Min Act: -0.1700
Data Index: 455308 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9050. Min Range: -6.9050
Max Act: 6.3113. Min Act: -0.1700
Data Index: 7312156 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19