Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5604 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.4348. Min Act: -0.1700
Data Index: 8355730 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.4348. Min Act: -0.1700
Data Index: 7245397 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.4035. Min Act: -0.1700
Data Index: 8627110 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.4035. Min Act: -0.1700
Data Index: 6780310 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.3722. Min Act: -0.1700
Data Index: 102225 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.3722. Min Act: -0.1700
Data Index: 427188 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.3410. Min Act: -0.1700
Data Index: 4648556 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.3097. Min Act: -0.1700
Data Index: 1701146 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.2785. Min Act: -0.1700
Data Index: 8335617 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.2785. Min Act: -0.1700
Data Index: 8450403 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.2785. Min Act: -0.1700
Data Index: 8798062 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.2472. Min Act: -0.1700
Data Index: 4213862 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.2785. Min Act: -0.1700
Data Index: 4265355 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.2472. Min Act: -0.1700
Data Index: 5926743 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.2472. Min Act: -0.1700
Data Index: 552772 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.2472. Min Act: -0.1700
Data Index: 7181044 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.2472. Min Act: -0.1700
Data Index: 8481488 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.2472. Min Act: -0.1700
Data Index: 5536892 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.2472. Min Act: -0.1700
Data Index: 844681 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4348. Min Range: -4.4348
Max Act: 4.2160. Min Act: -0.1700
Data Index: 5308425 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19