Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4782 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0319. Min Range: -5.0319
Max Act: 5.0006. Min Act: -0.1700
Data Index: 8428242 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0319. Min Range: -5.0319
Max Act: 5.0319. Min Act: -0.1700
Data Index: 4710228 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.8756. Min Act: -0.1700
Data Index: 600011 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.8756. Min Act: -0.1700
Data Index: 6868475 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.8756. Min Act: -0.1700
Data Index: 8315063 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.8756. Min Act: -0.1700
Data Index: 6252554 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.8444. Min Act: -0.1700
Data Index: 4689033 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.8444. Min Act: -0.1700
Data Index: 3514910 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.8131. Min Act: -0.1700
Data Index: 6929353 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.7819. Min Act: -0.1700
Data Index: 4671261 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.7819. Min Act: -0.1700
Data Index: 6090946 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.7819. Min Act: -0.1700
Data Index: 736382 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.7819. Min Act: -0.1700
Data Index: 6090944 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.7506. Min Act: -0.1700
Data Index: 5879405 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.7194. Min Act: -0.1700
Data Index: 2859412 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.7194. Min Act: -0.1700
Data Index: 7906859 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.7506. Min Act: -0.1700
Data Index: 1061841 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.7194. Min Act: -0.1700
Data Index: 5246477 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.7194. Min Act: -0.1700
Data Index: 1903914 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0319. Min Range: -5.0319
Max Act: 4.7194. Min Act: -0.1700
Data Index: 7130130 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19