Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2231 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.3726. Min Act: -0.1700
Data Index: 6269843 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2475. Min Act: -0.1700
Data Index: 7983025 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2163. Min Act: -0.1700
Data Index: 6155953 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.1538. Min Act: -0.1700
Data Index: 1962962 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.1225. Min Act: -0.1700
Data Index: 5786272 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.1225. Min Act: -0.1700
Data Index: 5673644 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.1538. Min Act: -0.1700
Data Index: 6818773 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.1225. Min Act: -0.1700
Data Index: 3332222 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.0913. Min Act: -0.1700
Data Index: 3830959 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.1225. Min Act: -0.1700
Data Index: 4090738 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.0913. Min Act: -0.1700
Data Index: 3865747 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.0913. Min Act: -0.1700
Data Index: 5681187 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.0913. Min Act: -0.1700
Data Index: 2086879 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.0600. Min Act: -0.1700
Data Index: 1308458 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.0288. Min Act: -0.1700
Data Index: 7848434 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.0288. Min Act: -0.1700
Data Index: 4128160 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.0288. Min Act: -0.1700
Data Index: 3033458 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.0913. Min Act: -0.1700
Data Index: 5030246 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.0288. Min Act: -0.1700
Data Index: 1239774 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.0288. Min Act: -0.1700
Data Index: 225776 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19