Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5362 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.7500. Min Act: -0.1700
Data Index: 2109413 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.6875. Min Act: -0.1700
Data Index: 7267080 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.5312. Min Act: -0.1700
Data Index: 7107435 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.5000. Min Act: -0.1700
Data Index: 946805 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.5000. Min Act: -0.1700
Data Index: 3132467 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.4375. Min Act: -0.1700
Data Index: 1121915 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.4062. Min Act: -0.1700
Data Index: 5755254 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.3750. Min Act: -0.1700
Data Index: 5514356 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.3437. Min Act: -0.1700
Data Index: 1489979 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.3437. Min Act: -0.1700
Data Index: 2501991 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.2812. Min Act: -0.1700
Data Index: 7796744 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.2812. Min Act: -0.1700
Data Index: 2172526 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.2812. Min Act: -0.1700
Data Index: 3885682 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.2500. Min Act: -0.1700
Data Index: 5877031 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.2500. Min Act: -0.1700
Data Index: 3182055 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.2812. Min Act: -0.1700
Data Index: 1723058 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.2500. Min Act: -0.1700
Data Index: 2546487 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.2187. Min Act: -0.1700
Data Index: 4213468 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.2500. Min Act: -0.1700
Data Index: 8390614 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7500. Min Range: -5.7500
Max Act: 5.2187. Min Act: -0.1700
Data Index: 4842400 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19