Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4087 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2831. Min Range: -7.2831
Max Act: 7.2831. Min Act: -0.1700
Data Index: 2449484 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2831. Min Range: -7.2831
Max Act: 7.2831. Min Act: -0.1700
Data Index: 3052657 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2831. Min Range: -7.2831
Max Act: 7.1893. Min Act: -0.1700
Data Index: 1931606 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2831. Min Range: -7.2831
Max Act: 7.0956. Min Act: -0.1700
Data Index: 2644494 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.8768. Min Act: -0.1700
Data Index: 2596425 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.8143. Min Act: -0.1700
Data Index: 8480090 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.7831. Min Act: -0.1700
Data Index: 8029104 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.7518. Min Act: -0.1700
Data Index: 5750262 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.7518. Min Act: -0.1700
Data Index: 4450566 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.7206. Min Act: -0.1700
Data Index: 3423930 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.7206. Min Act: -0.1700
Data Index: 8322106 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.6581. Min Act: -0.1700
Data Index: 5453431 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.6581. Min Act: -0.1700
Data Index: 282385 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.5643. Min Act: -0.1700
Data Index: 3190166 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.5956. Min Act: -0.1700
Data Index: 1894938 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.5331. Min Act: -0.1700
Data Index: 1118170 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.5331. Min Act: -0.1700
Data Index: 3871591 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.5018. Min Act: -0.1700
Data Index: 141656 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.5018. Min Act: -0.1700
Data Index: 7438368 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2831. Min Range: -7.2831
Max Act: 6.5018. Min Act: -0.1700
Data Index: 4501458 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19