Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3117 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.8132. Min Act: -0.1700
Data Index: 6054135 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.8132. Min Act: -0.1700
Data Index: 1254999 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.7194. Min Act: -0.1700
Data Index: 2386692 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.6881. Min Act: -0.1700
Data Index: 5666964 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.6255. Min Act: -0.1700
Data Index: 8292644 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.6099. Min Act: -0.1700
Data Index: 2713674 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.6099. Min Act: -0.1700
Data Index: 3563746 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.5942. Min Act: -0.1700
Data Index: 3498802 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.5316. Min Act: -0.1700
Data Index: 2073353 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.5316. Min Act: -0.1700
Data Index: 338331 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.4846. Min Act: -0.1700
Data Index: 7405957 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.4846. Min Act: -0.1700
Data Index: 2986485 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.4690. Min Act: -0.1700
Data Index: 1059188 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.4846. Min Act: -0.1700
Data Index: 6489106 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.4690. Min Act: -0.1700
Data Index: 2782110 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.4690. Min Act: -0.1700
Data Index: 7105597 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.4533. Min Act: -0.1700
Data Index: 6098880 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.4376. Min Act: -0.1700
Data Index: 7361361 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.4690. Min Act: -0.1700
Data Index: 2124015 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8132. Min Range: -3.8132
Max Act: 3.4376. Min Act: -0.1700
Data Index: 3425382 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19