Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4117 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3952. Min Range: -5.3952
Max Act: 5.3640. Min Act: -0.1700
Data Index: 5366114 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3952. Min Range: -5.3952
Max Act: 5.3952. Min Act: -0.1700
Data Index: 1246726 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3952. Min Range: -5.3952
Max Act: 5.1765. Min Act: -0.1700
Data Index: 3270992 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3952. Min Range: -5.3952
Max Act: 5.0827. Min Act: -0.1700
Data Index: 7654320 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3952. Min Range: -5.3952
Max Act: 5.1140. Min Act: -0.1700
Data Index: 8099059 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3952. Min Range: -5.3952
Max Act: 5.1140. Min Act: -0.1700
Data Index: 6551711 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3952. Min Range: -5.3952
Max Act: 5.1140. Min Act: -0.1700
Data Index: 766167 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3952. Min Range: -5.3952
Max Act: 5.1140. Min Act: -0.1700
Data Index: 7421459 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3952. Min Range: -5.3952
Max Act: 5.0515. Min Act: -0.1700
Data Index: 5051098 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3952. Min Range: -5.3952
Max Act: 5.0202. Min Act: -0.1700
Data Index: 6816711 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3952. Min Range: -5.3952
Max Act: 5.0202. Min Act: -0.1700
Data Index: 5329623 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3952. Min Range: -5.3952
Max Act: 5.0202. Min Act: -0.1700
Data Index: 8117897 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3952. Min Range: -5.3952
Max Act: 5.0202. Min Act: -0.1700
Data Index: 4403066 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3952. Min Range: -5.3952
Max Act: 4.9890. Min Act: -0.1700
Data Index: 6785163 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3952. Min Range: -5.3952
Max Act: 4.9890. Min Act: -0.1700
Data Index: 1850563 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3952. Min Range: -5.3952
Max Act: 4.9890. Min Act: -0.1700
Data Index: 4466119 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3952. Min Range: -5.3952
Max Act: 5.0202. Min Act: -0.1700
Data Index: 7169123 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3952. Min Range: -5.3952
Max Act: 4.9577. Min Act: -0.1700
Data Index: 3622364 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3952. Min Range: -5.3952
Max Act: 4.9577. Min Act: -0.1700
Data Index: 3734538 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3952. Min Range: -5.3952
Max Act: 4.9577. Min Act: -0.1700
Data Index: 2284520 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19