Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4134 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3032. Min Range: -7.3032
Max Act: 7.3032. Min Act: -0.1700
Data Index: 3458464 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.9282. Min Act: -0.1700
Data Index: 8350996 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.8657. Min Act: -0.1700
Data Index: 3074517 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.8657. Min Act: -0.1700
Data Index: 6026662 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.8657. Min Act: -0.1700
Data Index: 3869552 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.8032. Min Act: -0.1700
Data Index: 8683466 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.8345. Min Act: -0.1700
Data Index: 3917685 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.8345. Min Act: -0.1700
Data Index: 8773718 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.8032. Min Act: -0.1700
Data Index: 2566452 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.7720. Min Act: -0.1700
Data Index: 2603034 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.7720. Min Act: -0.1700
Data Index: 5149742 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.7407. Min Act: -0.1700
Data Index: 464756 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.7407. Min Act: -0.1700
Data Index: 8633406 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.7407. Min Act: -0.1700
Data Index: 303748 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.7095. Min Act: -0.1700
Data Index: 7426877 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.7095. Min Act: -0.1700
Data Index: 534698 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.6782. Min Act: -0.1700
Data Index: 7703445 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.6782. Min Act: -0.1700
Data Index: 4426108 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.6782. Min Act: -0.1700
Data Index: 3235444 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3032. Min Range: -7.3032
Max Act: 6.6470. Min Act: -0.1700
Data Index: 4727918 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19