Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 852 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5342. Min Range: -9.5342
Max Act: 9.5342. Min Act: -0.1700
Data Index: 8190405 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5342. Min Range: -9.5342
Max Act: 9.3467. Min Act: -0.1700
Data Index: 14431 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5342. Min Range: -9.5342
Max Act: 9.1592. Min Act: -0.1700
Data Index: 8521843 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5342. Min Range: -9.5342
Max Act: 9.0342. Min Act: -0.1700
Data Index: 8085907 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.9092. Min Act: -0.1700
Data Index: 4929043 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.9092. Min Act: -0.1700
Data Index: 87688 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.8467. Min Act: -0.1700
Data Index: 5280308 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.8467. Min Act: -0.1700
Data Index: 5146385 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.7842. Min Act: -0.1700
Data Index: 1451852 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.7842. Min Act: -0.1700
Data Index: 4880448 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.7217. Min Act: -0.1700
Data Index: 1048632 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.5967. Min Act: -0.1700
Data Index: 95263 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.5967. Min Act: -0.1700
Data Index: 2122940 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.5967. Min Act: -0.1700
Data Index: 1907902 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.5967. Min Act: -0.1700
Data Index: 2687171 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.5342. Min Act: -0.1700
Data Index: 6454604 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.5342. Min Act: -0.1700
Data Index: 4589977 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.5342. Min Act: -0.1700
Data Index: 4864114 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.5342. Min Act: -0.1700
Data Index: 4689953 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5342. Min Range: -9.5342
Max Act: 8.4717. Min Act: -0.1700
Data Index: 423061 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19