Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4436. Min Range: -9.4436
Max Act: 9.4436. Min Act: -0.1700
Data Index: 5374439 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4436. Min Range: -9.4436
Max Act: 9.0686. Min Act: -0.1700
Data Index: 4714838 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4436. Min Range: -9.4436
Max Act: 9.0061. Min Act: -0.1700
Data Index: 8810915 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.9436. Min Act: -0.1700
Data Index: 7159503 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.9436. Min Act: -0.1700
Data Index: 2836079 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.8811. Min Act: -0.1700
Data Index: 5565025 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.8186. Min Act: -0.1700
Data Index: 6474464 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.8186. Min Act: -0.1700
Data Index: 1830240 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.8186. Min Act: -0.1700
Data Index: 6656167 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.7561. Min Act: -0.1700
Data Index: 2932678 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.6936. Min Act: -0.1700
Data Index: 4226341 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.6936. Min Act: -0.1700
Data Index: 7917948 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.6936. Min Act: -0.1700
Data Index: 3910323 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.6936. Min Act: -0.1700
Data Index: 2293761 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.6311. Min Act: -0.1700
Data Index: 2773755 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.6311. Min Act: -0.1700
Data Index: 4958140 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.6311. Min Act: -0.1700
Data Index: 3689322 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.5686. Min Act: -0.1700
Data Index: 6961371 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.5061. Min Act: -0.1700
Data Index: 377047 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4436. Min Range: -9.4436
Max Act: 8.4436. Min Act: -0.1700
Data Index: 176849 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19