Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1365 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.7844. Min Act: -0.1700
Data Index: 1370058 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.6282. Min Act: -0.1700
Data Index: 5259829 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.5969. Min Act: -0.1700
Data Index: 5259830 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.5969. Min Act: -0.1700
Data Index: 6553828 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.5969. Min Act: -0.1700
Data Index: 3439202 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.5032. Min Act: -0.1700
Data Index: 5259828 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.5032. Min Act: -0.1700
Data Index: 3728776 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.5032. Min Act: -0.1700
Data Index: 278827 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.5032. Min Act: -0.1700
Data Index: 3647519 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.4719. Min Act: -0.1700
Data Index: 5618557 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.4407. Min Act: -0.1700
Data Index: 8229536 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.4094. Min Act: -0.1700
Data Index: 4967519 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.4094. Min Act: -0.1700
Data Index: 8021685 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.3782. Min Act: -0.1700
Data Index: 7198531 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.3782. Min Act: -0.1700
Data Index: 5047597 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.3782. Min Act: -0.1700
Data Index: 8270992 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.3469. Min Act: -0.1700
Data Index: 6455258 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.3469. Min Act: -0.1700
Data Index: 4143248 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.3469. Min Act: -0.1700
Data Index: 4484582 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7844. Min Range: -5.7844
Max Act: 5.3157. Min Act: -0.1700
Data Index: 1192215 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19