Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2268 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0518. Min Range: -4.0518
Max Act: 4.0518. Min Act: -0.1700
Data Index: 4943751 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.9893. Min Act: -0.1700
Data Index: 5490887 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.7391. Min Act: -0.1700
Data Index: 6659358 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.7078. Min Act: -0.1700
Data Index: 8097657 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.6609. Min Act: -0.1700
Data Index: 5599079 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.6453. Min Act: -0.1700
Data Index: 5776017 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.6453. Min Act: -0.1700
Data Index: 5318144 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.6140. Min Act: -0.1700
Data Index: 7049049 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.6140. Min Act: -0.1700
Data Index: 6201261 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.5983. Min Act: -0.1700
Data Index: 1486561 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.5983. Min Act: -0.1700
Data Index: 3992917 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.5827. Min Act: -0.1700
Data Index: 2983025 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.5670. Min Act: -0.1700
Data Index: 3735857 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.5827. Min Act: -0.1700
Data Index: 1557104 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.5513. Min Act: -0.1700
Data Index: 1560300 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.5513. Min Act: -0.1700
Data Index: 6361077 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.5513. Min Act: -0.1700
Data Index: 3001707 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.5200. Min Act: -0.1700
Data Index: 4510413 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.5044. Min Act: -0.1700
Data Index: 1170797 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0518. Min Range: -4.0518
Max Act: 3.5044. Min Act: -0.1700
Data Index: 3461805 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19