Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1478 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2105. Min Range: -5.2105
Max Act: 5.2105. Min Act: -0.1700
Data Index: 144396 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2105. Min Range: -5.2105
Max Act: 5.1792. Min Act: -0.1700
Data Index: 3398078 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2105. Min Range: -5.2105
Max Act: 5.1480. Min Act: -0.1700
Data Index: 1657473 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2105. Min Range: -5.2105
Max Act: 5.1480. Min Act: -0.1700
Data Index: 6834687 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2105. Min Range: -5.2105
Max Act: 5.1167. Min Act: -0.1700
Data Index: 841288 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2105. Min Range: -5.2105
Max Act: 5.1167. Min Act: -0.1700
Data Index: 8297390 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2105. Min Range: -5.2105
Max Act: 5.1167. Min Act: -0.1700
Data Index: 5735786 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2105. Min Range: -5.2105
Max Act: 5.0230. Min Act: -0.1700
Data Index: 8143685 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2105. Min Range: -5.2105
Max Act: 5.0230. Min Act: -0.1700
Data Index: 344106 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2105. Min Range: -5.2105
Max Act: 5.0230. Min Act: -0.1700
Data Index: 1417643 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2105. Min Range: -5.2105
Max Act: 4.9917. Min Act: -0.1700
Data Index: 2265361 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2105. Min Range: -5.2105
Max Act: 4.9917. Min Act: -0.1700
Data Index: 886946 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2105. Min Range: -5.2105
Max Act: 4.9605. Min Act: -0.1700
Data Index: 1101822 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2105. Min Range: -5.2105
Max Act: 4.9917. Min Act: -0.1700
Data Index: 8100391 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2105. Min Range: -5.2105
Max Act: 4.9917. Min Act: -0.1700
Data Index: 3398080 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2105. Min Range: -5.2105
Max Act: 4.9292. Min Act: -0.1700
Data Index: 3725860 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2105. Min Range: -5.2105
Max Act: 4.8980. Min Act: -0.1700
Data Index: 3713366 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2105. Min Range: -5.2105
Max Act: 4.8980. Min Act: -0.1700
Data Index: 7700485 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2105. Min Range: -5.2105
Max Act: 4.9292. Min Act: -0.1700
Data Index: 6373061 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2105. Min Range: -5.2105
Max Act: 4.8980. Min Act: -0.1700
Data Index: 2204059 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19