Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4966 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2393. Min Range: -7.2393
Max Act: 7.2393. Min Act: -0.1700
Data Index: 7448963 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.9268. Min Act: -0.1700
Data Index: 5390943 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.9268. Min Act: -0.1700
Data Index: 1188576 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.8956. Min Act: -0.1700
Data Index: 7852036 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.8018. Min Act: -0.1700
Data Index: 2603785 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.8018. Min Act: -0.1700
Data Index: 3489022 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.7393. Min Act: -0.1700
Data Index: 6608238 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.6768. Min Act: -0.1700
Data Index: 6871583 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.6456. Min Act: -0.1700
Data Index: 265831 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.6456. Min Act: -0.1700
Data Index: 3910732 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.6143. Min Act: -0.1700
Data Index: 8794718 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.6143. Min Act: -0.1700
Data Index: 1520634 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.6143. Min Act: -0.1700
Data Index: 6019522 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.6143. Min Act: -0.1700
Data Index: 8709431 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.6143. Min Act: -0.1700
Data Index: 260117 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.5831. Min Act: -0.1700
Data Index: 4387771 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.6143. Min Act: -0.1700
Data Index: 4039244 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.5831. Min Act: -0.1700
Data Index: 4108289 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.5518. Min Act: -0.1700
Data Index: 5968435 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2393. Min Range: -7.2393
Max Act: 6.5206. Min Act: -0.1700
Data Index: 3086552 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19