Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2523 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.7800. Min Act: -0.1700
Data Index: 2496361 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.7487. Min Act: -0.1700
Data Index: 152087 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.7331. Min Act: -0.1700
Data Index: 5635414 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.5923. Min Act: -0.1700
Data Index: 4465850 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.5610. Min Act: -0.1700
Data Index: 288456 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.5453. Min Act: -0.1700
Data Index: 576886 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.5453. Min Act: -0.1700
Data Index: 7520486 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.5296. Min Act: -0.1700
Data Index: 8328224 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.5140. Min Act: -0.1700
Data Index: 3204770 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.5140. Min Act: -0.1700
Data Index: 7367281 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.4983. Min Act: -0.1700
Data Index: 7578461 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.5140. Min Act: -0.1700
Data Index: 3916048 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.4827. Min Act: -0.1700
Data Index: 1856352 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.4827. Min Act: -0.1700
Data Index: 3839409 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.4513. Min Act: -0.1700
Data Index: 7262991 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.4513. Min Act: -0.1700
Data Index: 4198270 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.4357. Min Act: -0.1700
Data Index: 3948303 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.4513. Min Act: -0.1700
Data Index: 7494745 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.4357. Min Act: -0.1700
Data Index: 5939424 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7800. Min Range: -3.7800
Max Act: 3.4513. Min Act: -0.1700
Data Index: 3961408 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19