Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.5744. Min Act: -0.1700
Data Index: 3227832 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.5744. Min Act: -0.1700
Data Index: 4431649 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.5431. Min Act: -0.1700
Data Index: 8176212 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.5119. Min Act: -0.1700
Data Index: 6460366 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.5119. Min Act: -0.1700
Data Index: 6045550 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.5119. Min Act: -0.1700
Data Index: 6460367 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.5119. Min Act: -0.1700
Data Index: 310462 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.4494. Min Act: -0.1700
Data Index: 6437414 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.4806. Min Act: -0.1700
Data Index: 6936877 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.4494. Min Act: -0.1700
Data Index: 190422 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.4494. Min Act: -0.1700
Data Index: 4431656 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.4494. Min Act: -0.1700
Data Index: 5028840 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.4181. Min Act: -0.1700
Data Index: 190431 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.3869. Min Act: -0.1700
Data Index: 5037637 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.4181. Min Act: -0.1700
Data Index: 310487 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.4181. Min Act: -0.1700
Data Index: 2339490 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.3869. Min Act: -0.1700
Data Index: 8176214 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.3869. Min Act: -0.1700
Data Index: 5259381 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.3869. Min Act: -0.1700
Data Index: 5347457 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5744. Min Range: -5.5744
Max Act: 5.3869. Min Act: -0.1700
Data Index: 6246690 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19