Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6396 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4248. Min Range: -11.4248
Max Act: 11.4248. Min Act: -0.1700
Data Index: 6836920 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4248. Min Range: -11.4248
Max Act: 10.4873. Min Act: -0.1700
Data Index: 7160683 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4248. Min Range: -11.4248
Max Act: 10.3623. Min Act: -0.1700
Data Index: 260471 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4248. Min Range: -11.4248
Max Act: 10.2373. Min Act: -0.1700
Data Index: 4377579 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4248. Min Range: -11.4248
Max Act: 10.1123. Min Act: -0.1700
Data Index: 1644455 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4248. Min Range: -11.4248
Max Act: 10.1123. Min Act: -0.1700
Data Index: 6988442 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4248. Min Range: -11.4248
Max Act: 10.0498. Min Act: -0.1700
Data Index: 520259 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4248. Min Range: -11.4248
Max Act: 10.1123. Min Act: -0.1700
Data Index: 6988160 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4248. Min Range: -11.4248
Max Act: 10.0498. Min Act: -0.1700
Data Index: 2899070 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4248. Min Range: -11.4248
Max Act: 9.9873. Min Act: -0.1700
Data Index: 5248970 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4248. Min Range: -11.4248
Max Act: 9.9873. Min Act: -0.1700
Data Index: 3035123 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4248. Min Range: -11.4248
Max Act: 9.9873. Min Act: -0.1700
Data Index: 8065897 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4248. Min Range: -11.4248
Max Act: 9.9873. Min Act: -0.1700
Data Index: 1489313 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4248. Min Range: -11.4248
Max Act: 9.9873. Min Act: -0.1700
Data Index: 1536892 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4248. Min Range: -11.4248
Max Act: 10.0498. Min Act: -0.1700
Data Index: 7544719 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4248. Min Range: -11.4248
Max Act: 9.9873. Min Act: -0.1700
Data Index: 4377580 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4248. Min Range: -11.4248
Max Act: 9.9248. Min Act: -0.1700
Data Index: 8760585 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4248. Min Range: -11.4248
Max Act: 9.9248. Min Act: -0.1700
Data Index: 4285905 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4248. Min Range: -11.4248
Max Act: 9.9248. Min Act: -0.1700
Data Index: 8554209 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4248. Min Range: -11.4248
Max Act: 9.8623. Min Act: -0.1700
Data Index: 7230086 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19