Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3183 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1290. Min Range: -5.1290
Max Act: 5.1290. Min Act: -0.1700
Data Index: 1977861 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1290. Min Range: -5.1290
Max Act: 5.0353. Min Act: -0.1700
Data Index: 676384 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1290. Min Range: -5.1290
Max Act: 5.0040. Min Act: -0.1700
Data Index: 7424376 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.9728. Min Act: -0.1700
Data Index: 473683 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.9728. Min Act: -0.1700
Data Index: 7576805 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1290. Min Range: -5.1290
Max Act: 5.0040. Min Act: -0.1700
Data Index: 4952848 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.9103. Min Act: -0.1700
Data Index: 8339253 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.9415. Min Act: -0.1700
Data Index: 7262413 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.8478. Min Act: -0.1700
Data Index: 8223585 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.8478. Min Act: -0.1700
Data Index: 5369059 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.8478. Min Act: -0.1700
Data Index: 7465419 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.8478. Min Act: -0.1700
Data Index: 6848186 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.8165. Min Act: -0.1700
Data Index: 213995 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.8165. Min Act: -0.1700
Data Index: 607385 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.7853. Min Act: -0.1700
Data Index: 149222 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.7853. Min Act: -0.1700
Data Index: 6540744 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.7853. Min Act: -0.1700
Data Index: 5362066 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.7540. Min Act: -0.1700
Data Index: 4253603 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.7540. Min Act: -0.1700
Data Index: 4489514 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1290. Min Range: -5.1290
Max Act: 4.7540. Min Act: -0.1700
Data Index: 2519176 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19