Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1336 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0543. Min Range: -5.0543
Max Act: 5.0543. Min Act: -0.1700
Data Index: 8048563 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.9918. Min Act: -0.1700
Data Index: 7727145 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.9605. Min Act: -0.1700
Data Index: 3122813 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.9293. Min Act: -0.1700
Data Index: 1339539 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.8355. Min Act: -0.1700
Data Index: 4293296 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.8668. Min Act: -0.1700
Data Index: 4675983 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.8355. Min Act: -0.1700
Data Index: 761896 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.8355. Min Act: -0.1700
Data Index: 4712201 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.8355. Min Act: -0.1700
Data Index: 3732259 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.7730. Min Act: -0.1700
Data Index: 3122922 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.8043. Min Act: -0.1700
Data Index: 3527395 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.7418. Min Act: -0.1700
Data Index: 7957057 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.7418. Min Act: -0.1700
Data Index: 3058852 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.7418. Min Act: -0.1700
Data Index: 3361329 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.7730. Min Act: -0.1700
Data Index: 3265266 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.7105. Min Act: -0.1700
Data Index: 1906072 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.7105. Min Act: -0.1700
Data Index: 4297348 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.7105. Min Act: -0.1700
Data Index: 8237895 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.7105. Min Act: -0.1700
Data Index: 5364821 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0543. Min Range: -5.0543
Max Act: 4.7105. Min Act: -0.1700
Data Index: 253979 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19