Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2652 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5273. Min Range: -7.5273
Max Act: 7.5273. Min Act: -0.1700
Data Index: 6148402 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5273. Min Range: -7.5273
Max Act: 7.1523. Min Act: -0.1700
Data Index: 1246766 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5273. Min Range: -7.5273
Max Act: 7.1211. Min Act: -0.1700
Data Index: 5121034 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5273. Min Range: -7.5273
Max Act: 7.0586. Min Act: -0.1700
Data Index: 6228422 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.9336. Min Act: -0.1700
Data Index: 1324025 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.9023. Min Act: -0.1700
Data Index: 2236888 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.8711. Min Act: -0.1700
Data Index: 4838053 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.9023. Min Act: -0.1700
Data Index: 5561706 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.7773. Min Act: -0.1700
Data Index: 1938591 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.7461. Min Act: -0.1700
Data Index: 3856963 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.7461. Min Act: -0.1700
Data Index: 8285117 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.7148. Min Act: -0.1700
Data Index: 7111779 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.6523. Min Act: -0.1700
Data Index: 1218303 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.5898. Min Act: -0.1700
Data Index: 4222184 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.6211. Min Act: -0.1700
Data Index: 1570007 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.5898. Min Act: -0.1700
Data Index: 5726141 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.5586. Min Act: -0.1700
Data Index: 5209394 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.5586. Min Act: -0.1700
Data Index: 6960618 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.5273. Min Act: -0.1700
Data Index: 5721913 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5273. Min Range: -7.5273
Max Act: 6.4961. Min Act: -0.1700
Data Index: 5041087 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19