Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2650 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.9148. Min Act: -0.1700
Data Index: 3033059 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.8836. Min Act: -0.1700
Data Index: 4781631 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.8523. Min Act: -0.1700
Data Index: 4674566 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.7898. Min Act: -0.1700
Data Index: 2574226 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.7898. Min Act: -0.1700
Data Index: 5964873 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.7898. Min Act: -0.1700
Data Index: 4796798 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.7273. Min Act: -0.1700
Data Index: 1969422 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.7586. Min Act: -0.1700
Data Index: 8117325 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.7586. Min Act: -0.1700
Data Index: 4355510 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.7898. Min Act: -0.1700
Data Index: 4766906 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.7273. Min Act: -0.1700
Data Index: 4552941 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.7586. Min Act: -0.1700
Data Index: 8607939 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.7586. Min Act: -0.1700
Data Index: 8245949 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.7273. Min Act: -0.1700
Data Index: 4851762 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.6961. Min Act: -0.1700
Data Index: 1290823 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.7273. Min Act: -0.1700
Data Index: 2830345 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.6961. Min Act: -0.1700
Data Index: 5853485 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.6961. Min Act: -0.1700
Data Index: 5918625 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.6961. Min Act: -0.1700
Data Index: 4430874 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9148. Min Range: -6.9148
Max Act: 6.6961. Min Act: -0.1700
Data Index: 6289517 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19