Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 77 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.7282. Min Act: -0.1700
Data Index: 4630962 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.4782. Min Act: -0.1700
Data Index: 5966763 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.4157. Min Act: -0.1700
Data Index: 1904248 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.3532. Min Act: -0.1700
Data Index: 3238050 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.3219. Min Act: -0.1700
Data Index: 8038922 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.3219. Min Act: -0.1700
Data Index: 4362580 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.2907. Min Act: -0.1700
Data Index: 7896509 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.2594. Min Act: -0.1700
Data Index: 7896507 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.2907. Min Act: -0.1700
Data Index: 6699195 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.2907. Min Act: -0.1700
Data Index: 565153 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.2907. Min Act: -0.1700
Data Index: 5011515 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.2281. Min Act: -0.1700
Data Index: 6377921 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.2594. Min Act: -0.1700
Data Index: 7976423 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.2281. Min Act: -0.1700
Data Index: 5048274 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.2594. Min Act: -0.1700
Data Index: 6139931 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.2594. Min Act: -0.1700
Data Index: 8693540 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.2594. Min Act: -0.1700
Data Index: 8432563 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.2281. Min Act: -0.1700
Data Index: 1819924 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.2281. Min Act: -0.1700
Data Index: 4630961 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7282. Min Range: -4.7282
Max Act: 4.1969. Min Act: -0.1700
Data Index: 2170617 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19