Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6028 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.8389. Min Act: -0.1700
Data Index: 389891 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.6514. Min Act: -0.1700
Data Index: 5188764 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.6201. Min Act: -0.1700
Data Index: 7500356 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.6201. Min Act: -0.1700
Data Index: 6476384 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.5889. Min Act: -0.1700
Data Index: 6151560 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.5576. Min Act: -0.1700
Data Index: 650767 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.4951. Min Act: -0.1700
Data Index: 4053539 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.4951. Min Act: -0.1700
Data Index: 8068227 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.4639. Min Act: -0.1700
Data Index: 5804265 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.4639. Min Act: -0.1700
Data Index: 2263518 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.4326. Min Act: -0.1700
Data Index: 7224349 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.4326. Min Act: -0.1700
Data Index: 3802969 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.4014. Min Act: -0.1700
Data Index: 8327726 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.3701. Min Act: -0.1700
Data Index: 144737 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.3701. Min Act: -0.1700
Data Index: 650762 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.3389. Min Act: -0.1700
Data Index: 8086360 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.3389. Min Act: -0.1700
Data Index: 1668681 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.3076. Min Act: -0.1700
Data Index: 4660963 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.3076. Min Act: -0.1700
Data Index: 1488929 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8389. Min Range: -5.8389
Max Act: 5.3076. Min Act: -0.1700
Data Index: 2498300 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19