Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4808 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0894. Min Range: -5.0894
Max Act: 5.0894. Min Act: -0.1700
Data Index: 6425064 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.8394. Min Act: -0.1700
Data Index: 911185 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.8394. Min Act: -0.1700
Data Index: 3616610 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.8394. Min Act: -0.1700
Data Index: 4071684 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.8081. Min Act: -0.1700
Data Index: 4671770 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.8081. Min Act: -0.1700
Data Index: 4802341 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.7456. Min Act: -0.1700
Data Index: 6379069 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.7456. Min Act: -0.1700
Data Index: 5611335 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.7456. Min Act: -0.1700
Data Index: 3164014 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.7456. Min Act: -0.1700
Data Index: 2531841 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.7769. Min Act: -0.1700
Data Index: 4848230 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.7456. Min Act: -0.1700
Data Index: 3985273 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.7144. Min Act: -0.1700
Data Index: 185508 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.7144. Min Act: -0.1700
Data Index: 2115291 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.6831. Min Act: -0.1700
Data Index: 775173 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.6831. Min Act: -0.1700
Data Index: 3859819 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.6831. Min Act: -0.1700
Data Index: 7188347 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.7144. Min Act: -0.1700
Data Index: 7378881 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.7144. Min Act: -0.1700
Data Index: 8159389 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0894. Min Range: -5.0894
Max Act: 4.6519. Min Act: -0.1700
Data Index: 1011286 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19