Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4195 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3859. Min Range: -5.3859
Max Act: 5.3859. Min Act: -0.1700
Data Index: 6469018 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3859. Min Range: -5.3859
Max Act: 5.3546. Min Act: -0.1700
Data Index: 4500379 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3859. Min Range: -5.3859
Max Act: 5.1359. Min Act: -0.1700
Data Index: 3563964 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3859. Min Range: -5.3859
Max Act: 5.1046. Min Act: -0.1700
Data Index: 3428580 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3859. Min Range: -5.3859
Max Act: 5.0421. Min Act: -0.1700
Data Index: 5710828 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3859. Min Range: -5.3859
Max Act: 5.0421. Min Act: -0.1700
Data Index: 2320057 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3859. Min Range: -5.3859
Max Act: 5.0421. Min Act: -0.1700
Data Index: 1760979 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3859. Min Range: -5.3859
Max Act: 5.0109. Min Act: -0.1700
Data Index: 1296024 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3859. Min Range: -5.3859
Max Act: 4.9796. Min Act: -0.1700
Data Index: 3113795 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3859. Min Range: -5.3859
Max Act: 5.0109. Min Act: -0.1700
Data Index: 7055468 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3859. Min Range: -5.3859
Max Act: 5.0109. Min Act: -0.1700
Data Index: 1130793 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3859. Min Range: -5.3859
Max Act: 4.9796. Min Act: -0.1700
Data Index: 634907 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3859. Min Range: -5.3859
Max Act: 4.9484. Min Act: -0.1700
Data Index: 1913003 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3859. Min Range: -5.3859
Max Act: 5.0109. Min Act: -0.1700
Data Index: 3805071 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3859. Min Range: -5.3859
Max Act: 4.9171. Min Act: -0.1700
Data Index: 5032317 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3859. Min Range: -5.3859
Max Act: 4.9171. Min Act: -0.1700
Data Index: 237095 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3859. Min Range: -5.3859
Max Act: 4.9484. Min Act: -0.1700
Data Index: 4226584 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3859. Min Range: -5.3859
Max Act: 4.9171. Min Act: -0.1700
Data Index: 409283 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3859. Min Range: -5.3859
Max Act: 4.9171. Min Act: -0.1700
Data Index: 1223935 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3859. Min Range: -5.3859
Max Act: 4.9171. Min Act: -0.1700
Data Index: 2729654 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19