Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4241 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3184. Min Range: -4.3184
Max Act: 4.3184. Min Act: -0.1700
Data Index: 6098234 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3184. Min Range: -4.3184
Max Act: 4.2871. Min Act: -0.1700
Data Index: 3662890 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3184. Min Range: -4.3184
Max Act: 4.2246. Min Act: -0.1700
Data Index: 8711750 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3184. Min Range: -4.3184
Max Act: 4.2246. Min Act: -0.1700
Data Index: 345170 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3184. Min Range: -4.3184
Max Act: 4.1934. Min Act: -0.1700
Data Index: 7124358 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3184. Min Range: -4.3184
Max Act: 4.1309. Min Act: -0.1700
Data Index: 8692744 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3184. Min Range: -4.3184
Max Act: 4.1621. Min Act: -0.1700
Data Index: 1900059 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3184. Min Range: -4.3184
Max Act: 4.1621. Min Act: -0.1700
Data Index: 1222256 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3184. Min Range: -4.3184
Max Act: 4.0996. Min Act: -0.1700
Data Index: 6627595 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3184. Min Range: -4.3184
Max Act: 4.0371. Min Act: -0.1700
Data Index: 4443121 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3184. Min Range: -4.3184
Max Act: 4.0371. Min Act: -0.1700
Data Index: 7246832 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3184. Min Range: -4.3184
Max Act: 4.0058. Min Act: -0.1700
Data Index: 195945 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3184. Min Range: -4.3184
Max Act: 4.0371. Min Act: -0.1700
Data Index: 2936248 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3184. Min Range: -4.3184
Max Act: 4.0058. Min Act: -0.1700
Data Index: 7643668 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3184. Min Range: -4.3184
Max Act: 4.0058. Min Act: -0.1700
Data Index: 2348596 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3184. Min Range: -4.3184
Max Act: 3.9746. Min Act: -0.1700
Data Index: 4936029 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3184. Min Range: -4.3184
Max Act: 3.9433. Min Act: -0.1700
Data Index: 1281029 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3184. Min Range: -4.3184
Max Act: 3.9433. Min Act: -0.1700
Data Index: 4127101 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3184. Min Range: -4.3184
Max Act: 3.9433. Min Act: -0.1700
Data Index: 2562289 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3184. Min Range: -4.3184
Max Act: 3.9433. Min Act: -0.1700
Data Index: 2333447 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19