Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6065. Min Range: -6.6065
Max Act: 6.6065. Min Act: -0.1700
Data Index: 8493064 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6065. Min Range: -6.6065
Max Act: 6.6065. Min Act: -0.1700
Data Index: 1584162 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6065. Min Range: -6.6065
Max Act: 6.4503. Min Act: -0.1700
Data Index: 3807583 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6065. Min Range: -6.6065
Max Act: 6.2628. Min Act: -0.1700
Data Index: 52191 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6065. Min Range: -6.6065
Max Act: 6.2940. Min Act: -0.1700
Data Index: 4825045 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6065. Min Range: -6.6065
Max Act: 6.2003. Min Act: -0.1700
Data Index: 7684363 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6065. Min Range: -6.6065
Max Act: 6.1378. Min Act: -0.1700
Data Index: 2292080 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6065. Min Range: -6.6065
Max Act: 6.1065. Min Act: -0.1700
Data Index: 5009652 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6065. Min Range: -6.6065
Max Act: 6.0753. Min Act: -0.1700
Data Index: 3553680 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6065. Min Range: -6.6065
Max Act: 6.0440. Min Act: -0.1700
Data Index: 1012042 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6065. Min Range: -6.6065
Max Act: 6.0440. Min Act: -0.1700
Data Index: 7664806 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6065. Min Range: -6.6065
Max Act: 6.0440. Min Act: -0.1700
Data Index: 2216310 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6065. Min Range: -6.6065
Max Act: 6.0440. Min Act: -0.1700
Data Index: 1051714 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6065. Min Range: -6.6065
Max Act: 6.0440. Min Act: -0.1700
Data Index: 8520002 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6065. Min Range: -6.6065
Max Act: 6.0128. Min Act: -0.1700
Data Index: 3010207 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6065. Min Range: -6.6065
Max Act: 5.9815. Min Act: -0.1700
Data Index: 1719205 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6065. Min Range: -6.6065
Max Act: 5.9503. Min Act: -0.1700
Data Index: 3873847 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6065. Min Range: -6.6065
Max Act: 5.9503. Min Act: -0.1700
Data Index: 7324759 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6065. Min Range: -6.6065
Max Act: 5.9503. Min Act: -0.1700
Data Index: 6225684 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6065. Min Range: -6.6065
Max Act: 5.9503. Min Act: -0.1700
Data Index: 4502589 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19