Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2639 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.4298. Min Act: -0.1700
Data Index: 6147042 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.3360. Min Act: -0.1700
Data Index: 3251376 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.3360. Min Act: -0.1700
Data Index: 6731463 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.3048. Min Act: -0.1700
Data Index: 7631922 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.3048. Min Act: -0.1700
Data Index: 5888043 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.3048. Min Act: -0.1700
Data Index: 5337191 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.2735. Min Act: -0.1700
Data Index: 7785951 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.2735. Min Act: -0.1700
Data Index: 8784880 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.2423. Min Act: -0.1700
Data Index: 504848 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.2423. Min Act: -0.1700
Data Index: 1560073 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.2423. Min Act: -0.1700
Data Index: 4143405 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.2423. Min Act: -0.1700
Data Index: 6290564 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.2423. Min Act: -0.1700
Data Index: 6970170 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.1798. Min Act: -0.1700
Data Index: 1320782 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.2110. Min Act: -0.1700
Data Index: 7729996 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.1798. Min Act: -0.1700
Data Index: 7217111 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.2110. Min Act: -0.1700
Data Index: 5390202 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.1798. Min Act: -0.1700
Data Index: 7386669 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.1798. Min Act: -0.1700
Data Index: 1365182 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.2110. Min Act: -0.1700
Data Index: 5648514 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19