Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6559. Min Range: -5.6559
Max Act: 5.6559. Min Act: -0.1700
Data Index: 2499149 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6559. Min Range: -5.6559
Max Act: 5.2497. Min Act: -0.1700
Data Index: 2940780 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6559. Min Range: -5.6559
Max Act: 5.1872. Min Act: -0.1700
Data Index: 1387289 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6559. Min Range: -5.6559
Max Act: 5.1872. Min Act: -0.1700
Data Index: 8002742 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6559. Min Range: -5.6559
Max Act: 5.0309. Min Act: -0.1700
Data Index: 8186756 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6559. Min Range: -5.6559
Max Act: 4.9684. Min Act: -0.1700
Data Index: 5987683 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6559. Min Range: -5.6559
Max Act: 4.9372. Min Act: -0.1700
Data Index: 1114629 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6559. Min Range: -5.6559
Max Act: 4.9372. Min Act: -0.1700
Data Index: 5562328 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6559. Min Range: -5.6559
Max Act: 4.9372. Min Act: -0.1700
Data Index: 6270829 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6559. Min Range: -5.6559
Max Act: 4.9684. Min Act: -0.1700
Data Index: 5544716 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6559. Min Range: -5.6559
Max Act: 4.9684. Min Act: -0.1700
Data Index: 3330989 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6559. Min Range: -5.6559
Max Act: 4.9372. Min Act: -0.1700
Data Index: 5514942 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6559. Min Range: -5.6559
Max Act: 4.9372. Min Act: -0.1700
Data Index: 753039 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6559. Min Range: -5.6559
Max Act: 4.9372. Min Act: -0.1700
Data Index: 2079529 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6559. Min Range: -5.6559
Max Act: 4.9059. Min Act: -0.1700
Data Index: 6915757 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6559. Min Range: -5.6559
Max Act: 4.9059. Min Act: -0.1700
Data Index: 3399918 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6559. Min Range: -5.6559
Max Act: 4.9059. Min Act: -0.1700
Data Index: 5981247 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6559. Min Range: -5.6559
Max Act: 4.9059. Min Act: -0.1700
Data Index: 4298804 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6559. Min Range: -5.6559
Max Act: 4.8747. Min Act: -0.1700
Data Index: 4476194 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6559. Min Range: -5.6559
Max Act: 4.8747. Min Act: -0.1700
Data Index: 3793639 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19