Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.5439. Min Act: -0.1700
Data Index: 8140148 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.5752. Min Act: -0.1700
Data Index: 900448 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.5752. Min Act: -0.1700
Data Index: 6577441 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.5127. Min Act: -0.1700
Data Index: 4211796 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.5127. Min Act: -0.1700
Data Index: 3181689 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.4502. Min Act: -0.1700
Data Index: 1733742 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.3877. Min Act: -0.1700
Data Index: 7204122 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.3877. Min Act: -0.1700
Data Index: 7661801 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.3877. Min Act: -0.1700
Data Index: 900449 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.3877. Min Act: -0.1700
Data Index: 2698610 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.3877. Min Act: -0.1700
Data Index: 2843727 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.3564. Min Act: -0.1700
Data Index: 721962 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.3564. Min Act: -0.1700
Data Index: 6327143 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.3252. Min Act: -0.1700
Data Index: 721960 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.3564. Min Act: -0.1700
Data Index: 7204118 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.2939. Min Act: -0.1700
Data Index: 721951 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.2939. Min Act: -0.1700
Data Index: 1227523 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.3252. Min Act: -0.1700
Data Index: 4211797 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.3252. Min Act: -0.1700
Data Index: 7469790 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5752. Min Range: -4.5752
Max Act: 4.2939. Min Act: -0.1700
Data Index: 5566579 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19