Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4131 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0588. Min Range: -6.0588
Max Act: 6.0588. Min Act: -0.1700
Data Index: 19841 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.7463. Min Act: -0.1700
Data Index: 329256 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.7463. Min Act: -0.1700
Data Index: 3402356 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.5276. Min Act: -0.1700
Data Index: 7168889 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.5588. Min Act: -0.1700
Data Index: 4302046 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.5276. Min Act: -0.1700
Data Index: 5885929 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.4963. Min Act: -0.1700
Data Index: 686354 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.4651. Min Act: -0.1700
Data Index: 1768724 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.4651. Min Act: -0.1700
Data Index: 2850852 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.4651. Min Act: -0.1700
Data Index: 8227222 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.4338. Min Act: -0.1700
Data Index: 4858350 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.4338. Min Act: -0.1700
Data Index: 8823797 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.4338. Min Act: -0.1700
Data Index: 3636772 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.4026. Min Act: -0.1700
Data Index: 6807801 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.4338. Min Act: -0.1700
Data Index: 338816 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.4026. Min Act: -0.1700
Data Index: 8026559 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.3713. Min Act: -0.1700
Data Index: 530233 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.3713. Min Act: -0.1700
Data Index: 2430097 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.3713. Min Act: -0.1700
Data Index: 6914020 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0588. Min Range: -6.0588
Max Act: 5.3713. Min Act: -0.1700
Data Index: 4070463 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19