Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1568 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1367. Min Range: -4.1367
Max Act: 4.1367. Min Act: -0.1700
Data Index: 1372506 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1367. Min Range: -4.1367
Max Act: 4.0117. Min Act: -0.1700
Data Index: 2725530 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.9179. Min Act: -0.1700
Data Index: 3545029 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.8553. Min Act: -0.1700
Data Index: 4378716 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.8866. Min Act: -0.1700
Data Index: 5470218 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.8241. Min Act: -0.1700
Data Index: 7272903 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.8241. Min Act: -0.1700
Data Index: 1325294 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.7928. Min Act: -0.1700
Data Index: 7105087 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.7928. Min Act: -0.1700
Data Index: 2125902 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.7928. Min Act: -0.1700
Data Index: 7115034 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.7928. Min Act: -0.1700
Data Index: 813627 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.7615. Min Act: -0.1700
Data Index: 6449717 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.7615. Min Act: -0.1700
Data Index: 7062742 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.7615. Min Act: -0.1700
Data Index: 6272644 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.7615. Min Act: -0.1700
Data Index: 2513191 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.7615. Min Act: -0.1700
Data Index: 8237388 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.7928. Min Act: -0.1700
Data Index: 5885176 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.7302. Min Act: -0.1700
Data Index: 2813952 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.7615. Min Act: -0.1700
Data Index: 918410 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1367. Min Range: -4.1367
Max Act: 3.7302. Min Act: -0.1700
Data Index: 2404462 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19