Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.9019. Min Act: -0.1700
Data Index: 4117046 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.8394. Min Act: -0.1700
Data Index: 4117041 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.8394. Min Act: -0.1700
Data Index: 5639051 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.8394. Min Act: -0.1700
Data Index: 5530403 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.7769. Min Act: -0.1700
Data Index: 7670736 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.7457. Min Act: -0.1700
Data Index: 2197224 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.7144. Min Act: -0.1700
Data Index: 1490898 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6832. Min Act: -0.1700
Data Index: 7421356 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6832. Min Act: -0.1700
Data Index: 8098013 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6832. Min Act: -0.1700
Data Index: 5382102 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6832. Min Act: -0.1700
Data Index: 3187878 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6519. Min Act: -0.1700
Data Index: 3016032 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6519. Min Act: -0.1700
Data Index: 2240396 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6519. Min Act: -0.1700
Data Index: 1565126 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6207. Min Act: -0.1700
Data Index: 6153563 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6207. Min Act: -0.1700
Data Index: 4118788 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6207. Min Act: -0.1700
Data Index: 7859525 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.6207. Min Act: -0.1700
Data Index: 8676693 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.5894. Min Act: -0.1700
Data Index: 4777370 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9019. Min Range: -4.9019
Max Act: 4.5894. Min Act: -0.1700
Data Index: 6689036 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19