Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1851 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4099. Min Range: -7.4099
Max Act: 7.4099. Min Act: -0.1700
Data Index: 499665 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4099. Min Range: -7.4099
Max Act: 7.3786. Min Act: -0.1700
Data Index: 6183207 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4099. Min Range: -7.4099
Max Act: 7.3161. Min Act: -0.1700
Data Index: 3041666 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4099. Min Range: -7.4099
Max Act: 7.2849. Min Act: -0.1700
Data Index: 8175337 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4099. Min Range: -7.4099
Max Act: 7.1911. Min Act: -0.1700
Data Index: 4698746 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4099. Min Range: -7.4099
Max Act: 7.1599. Min Act: -0.1700
Data Index: 1360374 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4099. Min Range: -7.4099
Max Act: 7.0974. Min Act: -0.1700
Data Index: 3566880 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4099. Min Range: -7.4099
Max Act: 7.0661. Min Act: -0.1700
Data Index: 6878968 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4099. Min Range: -7.4099
Max Act: 7.0974. Min Act: -0.1700
Data Index: 7009157 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4099. Min Range: -7.4099
Max Act: 7.0661. Min Act: -0.1700
Data Index: 4116882 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4099. Min Range: -7.4099
Max Act: 7.0349. Min Act: -0.1700
Data Index: 627628 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4099. Min Range: -7.4099
Max Act: 7.0349. Min Act: -0.1700
Data Index: 7133409 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4099. Min Range: -7.4099
Max Act: 7.0036. Min Act: -0.1700
Data Index: 4623964 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4099. Min Range: -7.4099
Max Act: 6.9724. Min Act: -0.1700
Data Index: 2459316 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4099. Min Range: -7.4099
Max Act: 6.9724. Min Act: -0.1700
Data Index: 4677676 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4099. Min Range: -7.4099
Max Act: 6.9411. Min Act: -0.1700
Data Index: 2367477 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4099. Min Range: -7.4099
Max Act: 6.9411. Min Act: -0.1700
Data Index: 7276895 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4099. Min Range: -7.4099
Max Act: 6.8786. Min Act: -0.1700
Data Index: 3439334 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4099. Min Range: -7.4099
Max Act: 6.8786. Min Act: -0.1700
Data Index: 1138392 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4099. Min Range: -7.4099
Max Act: 6.8786. Min Act: -0.1700
Data Index: 1546835 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19