Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3490 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.8148. Min Act: -0.1700
Data Index: 2995241 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.6586. Min Act: -0.1700
Data Index: 1243477 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.5336. Min Act: -0.1700
Data Index: 3855751 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.5336. Min Act: -0.1700
Data Index: 2639989 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.5336. Min Act: -0.1700
Data Index: 1638700 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.5023. Min Act: -0.1700
Data Index: 8000480 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.5023. Min Act: -0.1700
Data Index: 6099638 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.4711. Min Act: -0.1700
Data Index: 5497451 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.4086. Min Act: -0.1700
Data Index: 6224791 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.3461. Min Act: -0.1700
Data Index: 7551073 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.3461. Min Act: -0.1700
Data Index: 1933059 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.3461. Min Act: -0.1700
Data Index: 3897244 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.3461. Min Act: -0.1700
Data Index: 2039417 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.3461. Min Act: -0.1700
Data Index: 302464 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.3461. Min Act: -0.1700
Data Index: 2228015 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.3148. Min Act: -0.1700
Data Index: 373569 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.3148. Min Act: -0.1700
Data Index: 529958 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.3148. Min Act: -0.1700
Data Index: 5454751 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.3148. Min Act: -0.1700
Data Index: 4951322 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8148. Min Range: -4.8148
Max Act: 4.3148. Min Act: -0.1700
Data Index: 1412102 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19