Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1572 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1429. Min Range: -6.1429
Max Act: 6.1429. Min Act: -0.1700
Data Index: 2454450 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1429. Min Range: -6.1429
Max Act: 6.0179. Min Act: -0.1700
Data Index: 2147360 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1429. Min Range: -6.1429
Max Act: 6.0179. Min Act: -0.1700
Data Index: 1773610 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.9867. Min Act: -0.1700
Data Index: 401083 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.9867. Min Act: -0.1700
Data Index: 2236343 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.9554. Min Act: -0.1700
Data Index: 1744052 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.9554. Min Act: -0.1700
Data Index: 1032965 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.9554. Min Act: -0.1700
Data Index: 4628660 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.8929. Min Act: -0.1700
Data Index: 8812955 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.8617. Min Act: -0.1700
Data Index: 2174623 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.8304. Min Act: -0.1700
Data Index: 7847557 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.7992. Min Act: -0.1700
Data Index: 982093 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.8617. Min Act: -0.1700
Data Index: 4225083 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.7992. Min Act: -0.1700
Data Index: 4782387 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.7679. Min Act: -0.1700
Data Index: 3170684 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.7992. Min Act: -0.1700
Data Index: 3340282 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.7679. Min Act: -0.1700
Data Index: 5389519 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.7367. Min Act: -0.1700
Data Index: 4892270 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.7367. Min Act: -0.1700
Data Index: 1965638 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1429. Min Range: -6.1429
Max Act: 5.7367. Min Act: -0.1700
Data Index: 2127013 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19