Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2181 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.7205. Min Act: -0.1700
Data Index: 2902237 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.5955. Min Act: -0.1700
Data Index: 7071652 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.5330. Min Act: -0.1700
Data Index: 2457356 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.5330. Min Act: -0.1699
Data Index: 4528804 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.4705. Min Act: -0.1700
Data Index: 7769042 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.4080. Min Act: -0.1700
Data Index: 3489061 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.4080. Min Act: -0.1690
Data Index: 5791865 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.2830. Min Act: -0.1700
Data Index: 5570163 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.3455. Min Act: -0.1668
Data Index: 7032734 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.2205. Min Act: -0.1509
Data Index: 4528799 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.2205. Min Act: -0.1535
Data Index: 4528803 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.2205. Min Act: -0.1664
Data Index: 2237725 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.1580. Min Act: -0.1700
Data Index: 5661363 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.2205. Min Act: -0.1395
Data Index: 7970524 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.1580. Min Act: -0.1690
Data Index: 6939279 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.1580. Min Act: -0.1695
Data Index: 7970523 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.1580. Min Act: -0.1700
Data Index: 1879738 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.0955. Min Act: -0.1700
Data Index: 166396 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.0955. Min Act: -0.1700
Data Index: 5001135 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7205. Min Range: -7.7205
Max Act: 7.0955. Min Act: -0.1673
Data Index: 121873 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19