Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1715 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.7599. Min Act: -0.1700
Data Index: 2989137 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.6662. Min Act: -0.1700
Data Index: 5972581 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.6662. Min Act: -0.1700
Data Index: 4453377 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.6349. Min Act: -0.1700
Data Index: 6101739 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.6349. Min Act: -0.1700
Data Index: 1264946 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.6037. Min Act: -0.1700
Data Index: 6490626 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.6037. Min Act: -0.1700
Data Index: 1264949 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.5724. Min Act: -0.1700
Data Index: 8345937 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.5099. Min Act: -0.1700
Data Index: 5837191 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.5099. Min Act: -0.1700
Data Index: 7915091 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.4787. Min Act: -0.1700
Data Index: 3470897 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.4162. Min Act: -0.1700
Data Index: 4385076 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.3849. Min Act: -0.1700
Data Index: 2408322 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.4162. Min Act: -0.1700
Data Index: 7662532 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.3849. Min Act: -0.1700
Data Index: 2818748 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.3849. Min Act: -0.1700
Data Index: 216458 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.3849. Min Act: -0.1700
Data Index: 6942855 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.3849. Min Act: -0.1700
Data Index: 7022845 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.3224. Min Act: -0.1700
Data Index: 2591310 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7599. Min Range: -4.7599
Max Act: 4.3537. Min Act: -0.1700
Data Index: 6333121 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19