Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1822 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.9822. Min Act: -0.1700
Data Index: 3560153 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.8884. Min Act: -0.1700
Data Index: 3234837 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.8259. Min Act: -0.1700
Data Index: 3309766 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.8259. Min Act: -0.1700
Data Index: 6752104 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.7633. Min Act: -0.1700
Data Index: 4262193 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.7633. Min Act: -0.1700
Data Index: 1620684 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.7633. Min Act: -0.1700
Data Index: 3344852 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.7633. Min Act: -0.1700
Data Index: 6394817 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.7320. Min Act: -0.1700
Data Index: 8003183 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.7164. Min Act: -0.1700
Data Index: 3344850 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.7477. Min Act: -0.1700
Data Index: 3201265 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.7320. Min Act: -0.1700
Data Index: 7811960 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.7320. Min Act: -0.1700
Data Index: 2684569 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.7164. Min Act: -0.1700
Data Index: 5584659 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.7008. Min Act: -0.1700
Data Index: 5948348 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.6851. Min Act: -0.1700
Data Index: 7152669 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.6851. Min Act: -0.1700
Data Index: 638776 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.7008. Min Act: -0.1700
Data Index: 6629130 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.6538. Min Act: -0.1700
Data Index: 4112869 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9822. Min Range: -3.9822
Max Act: 3.6695. Min Act: -0.1700
Data Index: 8497645 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19