Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3847 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.2389. Min Act: -0.1450
Data Index: 1583299 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.2389. Min Act: -0.1334
Data Index: 6033492 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.2300. Min Act: -0.1669
Data Index: 8141930 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.2300. Min Act: -0.1608
Data Index: 8696882 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.2124. Min Act: -0.1594
Data Index: 883835 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.2212. Min Act: -0.1647
Data Index: 646457 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.2124. Min Act: -0.1587
Data Index: 6776765 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.2036. Min Act: -0.1552
Data Index: 6899246 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.2036. Min Act: -0.1529
Data Index: 6057435 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.2036. Min Act: -0.1581
Data Index: 6888377 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.2124. Min Act: -0.1635
Data Index: 8809986 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.2124. Min Act: -0.1574
Data Index: 4661892 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.2036. Min Act: -0.1286
Data Index: 6734145 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.1948. Min Act: -0.1516
Data Index: 1684297 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.2036. Min Act: -0.1693
Data Index: 7444476 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.1948. Min Act: -0.1322
Data Index: 1612814 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.1948. Min Act: -0.1430
Data Index: 5643855 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.1860. Min Act: -0.1664
Data Index: 6526754 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.1860. Min Act: -0.1639
Data Index: 3051632 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2389. Min Range: -1.2389
Max Act: 1.1860. Min Act: -0.1224
Data Index: 3160247 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19