Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1125 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4459. Min Range: -5.4459
Max Act: 5.4459. Min Act: -0.1700
Data Index: 6464077 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4459. Min Range: -5.4459
Max Act: 5.3209. Min Act: -0.1700
Data Index: 4960984 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4459. Min Range: -5.4459
Max Act: 5.1646. Min Act: -0.1700
Data Index: 3444861 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4459. Min Range: -5.4459
Max Act: 5.0709. Min Act: -0.1700
Data Index: 8443731 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4459. Min Range: -5.4459
Max Act: 5.0084. Min Act: -0.1700
Data Index: 6896992 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4459. Min Range: -5.4459
Max Act: 5.0084. Min Act: -0.1700
Data Index: 1370471 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4459. Min Range: -5.4459
Max Act: 5.0396. Min Act: -0.1700
Data Index: 8699312 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4459. Min Range: -5.4459
Max Act: 4.9771. Min Act: -0.1700
Data Index: 2109649 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4459. Min Range: -5.4459
Max Act: 4.9459. Min Act: -0.1700
Data Index: 823437 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4459. Min Range: -5.4459
Max Act: 4.9771. Min Act: -0.1700
Data Index: 6932697 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4459. Min Range: -5.4459
Max Act: 4.9146. Min Act: -0.1700
Data Index: 8040647 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4459. Min Range: -5.4459
Max Act: 4.9459. Min Act: -0.1700
Data Index: 4502765 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4459. Min Range: -5.4459
Max Act: 4.9459. Min Act: -0.1700
Data Index: 602624 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4459. Min Range: -5.4459
Max Act: 4.9459. Min Act: -0.1700
Data Index: 6239729 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4459. Min Range: -5.4459
Max Act: 4.9146. Min Act: -0.1700
Data Index: 6966264 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4459. Min Range: -5.4459
Max Act: 4.8834. Min Act: -0.1700
Data Index: 6263633 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4459. Min Range: -5.4459
Max Act: 4.8521. Min Act: -0.1700
Data Index: 2945364 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4459. Min Range: -5.4459
Max Act: 4.8834. Min Act: -0.1700
Data Index: 333693 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4459. Min Range: -5.4459
Max Act: 4.8834. Min Act: -0.1700
Data Index: 4254831 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4459. Min Range: -5.4459
Max Act: 4.8834. Min Act: -0.1700
Data Index: 8625962 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19