Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5444 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1158. Min Range: -7.1158
Max Act: 7.1158. Min Act: -0.1700
Data Index: 4715808 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.7721. Min Act: -0.1700
Data Index: 7871683 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.6783. Min Act: -0.1700
Data Index: 5155363 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.6783. Min Act: -0.1700
Data Index: 4579853 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.5846. Min Act: -0.1700
Data Index: 2535045 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.5846. Min Act: -0.1700
Data Index: 8556422 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.5846. Min Act: -0.1700
Data Index: 8090003 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.5533. Min Act: -0.1700
Data Index: 2688384 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.5533. Min Act: -0.1700
Data Index: 4377935 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.5846. Min Act: -0.1700
Data Index: 8589067 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.5221. Min Act: -0.1700
Data Index: 3326104 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.5533. Min Act: -0.1700
Data Index: 5823102 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.5533. Min Act: -0.1700
Data Index: 3497260 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.5533. Min Act: -0.1700
Data Index: 5404626 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.4908. Min Act: -0.1700
Data Index: 3125321 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.4908. Min Act: -0.1700
Data Index: 6597473 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.4596. Min Act: -0.1700
Data Index: 3564981 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.4596. Min Act: -0.1700
Data Index: 6302688 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.4596. Min Act: -0.1700
Data Index: 259618 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1158. Min Range: -7.1158
Max Act: 6.3971. Min Act: -0.1700
Data Index: 4548178 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19