Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2983 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.2676. Min Act: -0.1700
Data Index: 2909106 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.2500. Min Act: -0.1700
Data Index: 3662492 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.2147. Min Act: -0.1699
Data Index: 6547942 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.2147. Min Act: -0.1683
Data Index: 4348265 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.2147. Min Act: -0.1699
Data Index: 6547940 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.1795. Min Act: -0.1698
Data Index: 4626496 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.1795. Min Act: -0.1699
Data Index: 3662493 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.1619. Min Act: -0.1691
Data Index: 4626492 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.1619. Min Act: -0.1689
Data Index: 2990704 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.1619. Min Act: -0.1601
Data Index: 6547941 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.1268. Min Act: -0.1700
Data Index: 8758126 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.1268. Min Act: -0.1700
Data Index: 2990702 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.1092. Min Act: -0.1698
Data Index: 452240 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.1092. Min Act: -0.1650
Data Index: 2990703 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.1005. Min Act: -0.1698
Data Index: 2512711 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.1005. Min Act: -0.1698
Data Index: 2990698 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.1005. Min Act: -0.1695
Data Index: 4986273 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.0917. Min Act: -0.1700
Data Index: 4673653 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.0917. Min Act: -0.1700
Data Index: 4011627 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2676. Min Range: -1.2676
Max Act: 1.0830. Min Act: -0.1688
Data Index: 4626494 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19