Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2529 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2202. Min Range: -3.2202
Max Act: 3.2202. Min Act: -0.1700
Data Index: 5863391 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2202. Min Range: -3.2202
Max Act: 3.0470. Min Act: -0.1700
Data Index: 8815819 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2202. Min Range: -3.2202
Max Act: 3.0470. Min Act: -0.1700
Data Index: 794086 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2202. Min Range: -3.2202
Max Act: 3.0470. Min Act: -0.1700
Data Index: 7016794 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2202. Min Range: -3.2202
Max Act: 3.0627. Min Act: -0.1700
Data Index: 8173063 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2202. Min Range: -3.2202
Max Act: 3.0154. Min Act: -0.1700
Data Index: 3602763 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2202. Min Range: -3.2202
Max Act: 3.0627. Min Act: -0.1700
Data Index: 4493115 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2202. Min Range: -3.2202
Max Act: 3.0312. Min Act: -0.1700
Data Index: 249109 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2202. Min Range: -3.2202
Max Act: 2.9996. Min Act: -0.1700
Data Index: 1549641 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2202. Min Range: -3.2202
Max Act: 2.9838. Min Act: -0.1700
Data Index: 8651290 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2202. Min Range: -3.2202
Max Act: 2.9996. Min Act: -0.1700
Data Index: 6758641 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2202. Min Range: -3.2202
Max Act: 2.9679. Min Act: -0.1700
Data Index: 118034 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2202. Min Range: -3.2202
Max Act: 2.9204. Min Act: -0.1700
Data Index: 6960915 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2202. Min Range: -3.2202
Max Act: 2.9521. Min Act: -0.1700
Data Index: 3310968 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2202. Min Range: -3.2202
Max Act: 2.9521. Min Act: -0.1700
Data Index: 8230178 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2202. Min Range: -3.2202
Max Act: 2.9521. Min Act: -0.1700
Data Index: 6080160 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2202. Min Range: -3.2202
Max Act: 2.9204. Min Act: -0.1700
Data Index: 1360536 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2202. Min Range: -3.2202
Max Act: 2.9204. Min Act: -0.1700
Data Index: 6573026 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2202. Min Range: -3.2202
Max Act: 2.9521. Min Act: -0.1700
Data Index: 4572977 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2202. Min Range: -3.2202
Max Act: 2.9363. Min Act: -0.1700
Data Index: 1960826 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19