Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 55 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3998. Min Range: -6.3998
Max Act: 6.3998. Min Act: -0.1700
Data Index: 6193118 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3998. Min Range: -6.3998
Max Act: 6.3373. Min Act: -0.1700
Data Index: 2508742 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3998. Min Range: -6.3998
Max Act: 6.3373. Min Act: -0.1700
Data Index: 7306167 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3998. Min Range: -6.3998
Max Act: 6.2435. Min Act: -0.1700
Data Index: 3391039 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3998. Min Range: -6.3998
Max Act: 6.2123. Min Act: -0.1700
Data Index: 5627896 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3998. Min Range: -6.3998
Max Act: 6.1185. Min Act: -0.1700
Data Index: 3768058 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3998. Min Range: -6.3998
Max Act: 6.1185. Min Act: -0.1700
Data Index: 3095604 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3998. Min Range: -6.3998
Max Act: 6.0560. Min Act: -0.1700
Data Index: 910189 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3998. Min Range: -6.3998
Max Act: 6.0560. Min Act: -0.1700
Data Index: 7348380 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3998. Min Range: -6.3998
Max Act: 6.0560. Min Act: -0.1700
Data Index: 1244890 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3998. Min Range: -6.3998
Max Act: 6.0873. Min Act: -0.1700
Data Index: 8552243 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3998. Min Range: -6.3998
Max Act: 6.0560. Min Act: -0.1700
Data Index: 5429954 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3998. Min Range: -6.3998
Max Act: 6.0248. Min Act: -0.1700
Data Index: 4894951 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3998. Min Range: -6.3998
Max Act: 6.0248. Min Act: -0.1700
Data Index: 3365941 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3998. Min Range: -6.3998
Max Act: 5.9935. Min Act: -0.1700
Data Index: 7625321 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3998. Min Range: -6.3998
Max Act: 5.9935. Min Act: -0.1700
Data Index: 4900923 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3998. Min Range: -6.3998
Max Act: 5.9935. Min Act: -0.1700
Data Index: 1137903 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3998. Min Range: -6.3998
Max Act: 5.9623. Min Act: -0.1700
Data Index: 7348382 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3998. Min Range: -6.3998
Max Act: 5.9310. Min Act: -0.1700
Data Index: 4696038 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3998. Min Range: -6.3998
Max Act: 5.9310. Min Act: -0.1700
Data Index: 4249242 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19