Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 587 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.6802. Min Act: -0.1700
Data Index: 4463056 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.6489. Min Act: -0.1700
Data Index: 693178 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.6176. Min Act: -0.1700
Data Index: 3359129 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.6176. Min Act: -0.1700
Data Index: 8607996 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.6176. Min Act: -0.1700
Data Index: 3684950 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.6176. Min Act: -0.1700
Data Index: 5792 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.6176. Min Act: -0.1700
Data Index: 7254483 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.6176. Min Act: -0.1700
Data Index: 5212187 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.5863. Min Act: -0.1700
Data Index: 7948291 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.5863. Min Act: -0.1700
Data Index: 7946302 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.5863. Min Act: -0.1700
Data Index: 6959283 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.5863. Min Act: -0.1700
Data Index: 2599336 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.5863. Min Act: -0.1700
Data Index: 900180 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.5863. Min Act: -0.1700
Data Index: 862934 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.5863. Min Act: -0.1700
Data Index: 5972152 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.5863. Min Act: -0.1700
Data Index: 5820652 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.5863. Min Act: -0.1700
Data Index: 5233991 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.5863. Min Act: -0.1700
Data Index: 4666283 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.5863. Min Act: -0.1700
Data Index: 755346 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6802. Min Range: -3.6802
Max Act: 3.5863. Min Act: -0.1700
Data Index: 3389465 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19