Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2692 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4093. Min Range: -6.4093
Max Act: 6.4093. Min Act: -0.1700
Data Index: 8174065 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4093. Min Range: -6.4093
Max Act: 6.3781. Min Act: -0.1700
Data Index: 2112769 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4093. Min Range: -6.4093
Max Act: 6.2218. Min Act: -0.1700
Data Index: 642854 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4093. Min Range: -6.4093
Max Act: 6.0343. Min Act: -0.1700
Data Index: 5294194 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4093. Min Range: -6.4093
Max Act: 6.0343. Min Act: -0.1700
Data Index: 7056534 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4093. Min Range: -6.4093
Max Act: 5.8468. Min Act: -0.1700
Data Index: 3471022 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4093. Min Range: -6.4093
Max Act: 5.8781. Min Act: -0.1700
Data Index: 108457 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4093. Min Range: -6.4093
Max Act: 5.8468. Min Act: -0.1700
Data Index: 6194708 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4093. Min Range: -6.4093
Max Act: 5.8156. Min Act: -0.1700
Data Index: 4608803 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4093. Min Range: -6.4093
Max Act: 5.8468. Min Act: -0.1700
Data Index: 4438620 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4093. Min Range: -6.4093
Max Act: 5.8156. Min Act: -0.1700
Data Index: 2478889 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4093. Min Range: -6.4093
Max Act: 5.8468. Min Act: -0.1700
Data Index: 6161129 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4093. Min Range: -6.4093
Max Act: 5.8156. Min Act: -0.1700
Data Index: 1479562 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4093. Min Range: -6.4093
Max Act: 5.8468. Min Act: -0.1700
Data Index: 3395467 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4093. Min Range: -6.4093
Max Act: 5.8156. Min Act: -0.1700
Data Index: 6943462 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4093. Min Range: -6.4093
Max Act: 5.8156. Min Act: -0.1700
Data Index: 4318703 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4093. Min Range: -6.4093
Max Act: 5.8156. Min Act: -0.1700
Data Index: 6845486 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4093. Min Range: -6.4093
Max Act: 5.7531. Min Act: -0.1700
Data Index: 4223336 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4093. Min Range: -6.4093
Max Act: 5.7531. Min Act: -0.1700
Data Index: 4392050 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4093. Min Range: -6.4093
Max Act: 5.7218. Min Act: -0.1700
Data Index: 7136930 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19