Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.9157. Min Act: -0.1700
Data Index: 7715407 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.6657. Min Act: -0.1700
Data Index: 2969022 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.6345. Min Act: -0.1700
Data Index: 1274639 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.6032. Min Act: -0.1700
Data Index: 7376219 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.5720. Min Act: -0.1700
Data Index: 6203124 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.5720. Min Act: -0.1700
Data Index: 4303733 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.5407. Min Act: -0.1700
Data Index: 6644950 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.5720. Min Act: -0.1700
Data Index: 7094392 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.5720. Min Act: -0.1700
Data Index: 4603195 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.5407. Min Act: -0.1700
Data Index: 8670791 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.5407. Min Act: -0.1700
Data Index: 2481883 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.5407. Min Act: -0.1700
Data Index: 5303112 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.5407. Min Act: -0.1700
Data Index: 7301748 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.5407. Min Act: -0.1700
Data Index: 1292681 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.5407. Min Act: -0.1700
Data Index: 3338794 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.5095. Min Act: -0.1700
Data Index: 1192765 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.5095. Min Act: -0.1700
Data Index: 5679213 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.4782. Min Act: -0.1700
Data Index: 5007763 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.4782. Min Act: -0.1700
Data Index: 168648 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9157. Min Range: -6.9157
Max Act: 6.5095. Min Act: -0.1700
Data Index: 867644 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19