Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4379 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6328. Min Range: -6.6328
Max Act: 6.6328. Min Act: -0.1700
Data Index: 4600438 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6328. Min Range: -6.6328
Max Act: 6.5078. Min Act: -0.1700
Data Index: 5645353 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6328. Min Range: -6.6328
Max Act: 6.2578. Min Act: -0.1700
Data Index: 1529190 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6328. Min Range: -6.6328
Max Act: 6.2578. Min Act: -0.1700
Data Index: 4375215 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6328. Min Range: -6.6328
Max Act: 6.1328. Min Act: -0.1700
Data Index: 6225648 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6328. Min Range: -6.6328
Max Act: 6.1328. Min Act: -0.1700
Data Index: 3878707 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6328. Min Range: -6.6328
Max Act: 6.0703. Min Act: -0.1700
Data Index: 6377889 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6328. Min Range: -6.6328
Max Act: 6.0703. Min Act: -0.1700
Data Index: 195521 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6328. Min Range: -6.6328
Max Act: 6.0703. Min Act: -0.1700
Data Index: 4154498 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6328. Min Range: -6.6328
Max Act: 6.0391. Min Act: -0.1700
Data Index: 1126994 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6328. Min Range: -6.6328
Max Act: 6.0391. Min Act: -0.1700
Data Index: 4420852 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6328. Min Range: -6.6328
Max Act: 6.0078. Min Act: -0.1700
Data Index: 764889 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6328. Min Range: -6.6328
Max Act: 6.0078. Min Act: -0.1700
Data Index: 3005424 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6328. Min Range: -6.6328
Max Act: 6.0078. Min Act: -0.1700
Data Index: 7881224 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6328. Min Range: -6.6328
Max Act: 6.0078. Min Act: -0.1700
Data Index: 8586124 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6328. Min Range: -6.6328
Max Act: 5.9766. Min Act: -0.1700
Data Index: 2986237 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6328. Min Range: -6.6328
Max Act: 5.9453. Min Act: -0.1700
Data Index: 788934 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6328. Min Range: -6.6328
Max Act: 5.9453. Min Act: -0.1700
Data Index: 4817266 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6328. Min Range: -6.6328
Max Act: 5.9141. Min Act: -0.1700
Data Index: 4347964 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6328. Min Range: -6.6328
Max Act: 5.9453. Min Act: -0.1700
Data Index: 598666 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19