Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4565 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.7934. Min Act: -0.1700
Data Index: 1587229 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.6059. Min Act: -0.1700
Data Index: 7007106 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.5434. Min Act: -0.1700
Data Index: 4755959 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.4809. Min Act: -0.1700
Data Index: 7820189 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.4184. Min Act: -0.1700
Data Index: 6247181 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.2934. Min Act: -0.1700
Data Index: 3212878 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.2309. Min Act: -0.1700
Data Index: 743134 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.2309. Min Act: -0.1700
Data Index: 2157247 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.2309. Min Act: -0.1700
Data Index: 6806252 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.2309. Min Act: -0.1700
Data Index: 3991175 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.2309. Min Act: -0.1700
Data Index: 6990044 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.1684. Min Act: -0.1700
Data Index: 5689083 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.1684. Min Act: -0.1700
Data Index: 7107576 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.1059. Min Act: -0.1700
Data Index: 75584 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.0434. Min Act: -0.1700
Data Index: 2394715 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.0434. Min Act: -0.1700
Data Index: 7420755 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.0434. Min Act: -0.1700
Data Index: 7095206 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.0434. Min Act: -0.1700
Data Index: 2067406 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.0434. Min Act: -0.1700
Data Index: 1834622 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7934. Min Range: -8.7934
Max Act: 8.0434. Min Act: -0.1700
Data Index: 2910144 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19