Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3918 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.8171. Min Act: -0.1700
Data Index: 2210011 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.6921. Min Act: -0.1700
Data Index: 7911050 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.5983. Min Act: -0.1700
Data Index: 4747452 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.6296. Min Act: -0.1700
Data Index: 363563 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.5983. Min Act: -0.1700
Data Index: 4103867 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.5046. Min Act: -0.1700
Data Index: 649373 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.5046. Min Act: -0.1700
Data Index: 52487 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.4733. Min Act: -0.1700
Data Index: 5348132 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.4421. Min Act: -0.1700
Data Index: 7959452 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.4108. Min Act: -0.1700
Data Index: 1626475 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.4421. Min Act: -0.1700
Data Index: 4460333 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.4108. Min Act: -0.1700
Data Index: 713047 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.3796. Min Act: -0.1700
Data Index: 4332793 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.3796. Min Act: -0.1700
Data Index: 2537860 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.3483. Min Act: -0.1700
Data Index: 3535993 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.3796. Min Act: -0.1700
Data Index: 4448101 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.3796. Min Act: -0.1700
Data Index: 2724280 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.3796. Min Act: -0.1700
Data Index: 3514082 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.3483. Min Act: -0.1700
Data Index: 1370293 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8171. Min Range: -5.8171
Max Act: 5.3483. Min Act: -0.1700
Data Index: 8792586 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19