Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4380 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.5604. Min Act: -0.1700
Data Index: 7373788 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.5604. Min Act: -0.1700
Data Index: 3854978 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.5604. Min Act: -0.1700
Data Index: 7568155 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.4979. Min Act: -0.1700
Data Index: 8675494 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.3729. Min Act: -0.1700
Data Index: 3891341 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.3416. Min Act: -0.1700
Data Index: 5718035 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.3416. Min Act: -0.1700
Data Index: 4956696 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.3416. Min Act: -0.1700
Data Index: 7066690 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.1854. Min Act: -0.1700
Data Index: 5398324 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.1854. Min Act: -0.1700
Data Index: 213256 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.2166. Min Act: -0.1700
Data Index: 7866388 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.2166. Min Act: -0.1700
Data Index: 358869 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.2166. Min Act: -0.1700
Data Index: 3103470 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.1854. Min Act: -0.1700
Data Index: 4006458 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.1854. Min Act: -0.1700
Data Index: 854275 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.1541. Min Act: -0.1700
Data Index: 2434449 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.1854. Min Act: -0.1700
Data Index: 7339756 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.1541. Min Act: -0.1700
Data Index: 7250175 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.1229. Min Act: -0.1700
Data Index: 194946 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5604. Min Range: -5.5604
Max Act: 5.1229. Min Act: -0.1700
Data Index: 5002194 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19