Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4552 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.4191. Min Act: -0.1700
Data Index: 7042769 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.3253. Min Act: -0.1700
Data Index: 2889662 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.2003. Min Act: -0.1700
Data Index: 6075582 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.2003. Min Act: -0.1700
Data Index: 4382904 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.2003. Min Act: -0.1700
Data Index: 2735533 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.2003. Min Act: -0.1700
Data Index: 6375884 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.1378. Min Act: -0.1700
Data Index: 7441757 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.1066. Min Act: -0.1700
Data Index: 6761622 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.1066. Min Act: -0.1700
Data Index: 7448465 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.1066. Min Act: -0.1700
Data Index: 3586892 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.1378. Min Act: -0.1700
Data Index: 7223686 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.0753. Min Act: -0.1700
Data Index: 2609681 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.0753. Min Act: -0.1700
Data Index: 4693524 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.0753. Min Act: -0.1700
Data Index: 6964278 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.0753. Min Act: -0.1700
Data Index: 6471627 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.0441. Min Act: -0.1700
Data Index: 6648271 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4191. Min Range: -5.4191
Max Act: 5.0128. Min Act: -0.1700
Data Index: 4311560 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4191. Min Range: -5.4191
Max Act: 4.9816. Min Act: -0.1700
Data Index: 4525198 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4191. Min Range: -5.4191
Max Act: 4.9816. Min Act: -0.1700
Data Index: 946056 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4191. Min Range: -5.4191
Max Act: 4.9816. Min Act: -0.1700
Data Index: 7215797 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19