Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5396 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.6890. Min Act: -0.1700
Data Index: 2804014 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.6890. Min Act: -0.1700
Data Index: 2023875 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.6577. Min Act: -0.1700
Data Index: 2083730 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.6265. Min Act: -0.1700
Data Index: 7720607 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.6265. Min Act: -0.1700
Data Index: 4520463 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.5952. Min Act: -0.1700
Data Index: 8816823 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.5952. Min Act: -0.1700
Data Index: 258385 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.5952. Min Act: -0.1700
Data Index: 779000 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.5327. Min Act: -0.1700
Data Index: 23188 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.5327. Min Act: -0.1700
Data Index: 1323710 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.5327. Min Act: -0.1700
Data Index: 8294769 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.5015. Min Act: -0.1700
Data Index: 2278132 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.4702. Min Act: -0.1700
Data Index: 1392632 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.5015. Min Act: -0.1700
Data Index: 6316875 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.4702. Min Act: -0.1700
Data Index: 2917418 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.4702. Min Act: -0.1700
Data Index: 1488490 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.4702. Min Act: -0.1700
Data Index: 4772216 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.4390. Min Act: -0.1700
Data Index: 4033012 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.4390. Min Act: -0.1700
Data Index: 6229166 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6890. Min Range: -5.6890
Max Act: 5.4077. Min Act: -0.1700
Data Index: 5647400 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19