Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5766 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0928. Min Range: -6.0928
Max Act: 6.0928. Min Act: -0.1700
Data Index: 4665785 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0928. Min Range: -6.0928
Max Act: 6.0928. Min Act: -0.1700
Data Index: 1955464 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.9678. Min Act: -0.1700
Data Index: 4665786 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.9366. Min Act: -0.1700
Data Index: 2455117 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.9053. Min Act: -0.1700
Data Index: 1318564 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.8428. Min Act: -0.1700
Data Index: 7302003 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.7803. Min Act: -0.1700
Data Index: 6021952 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.7491. Min Act: -0.1700
Data Index: 5855511 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.7491. Min Act: -0.1700
Data Index: 7061163 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.7491. Min Act: -0.1700
Data Index: 3535451 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.7491. Min Act: -0.1700
Data Index: 5025348 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.6866. Min Act: -0.1700
Data Index: 8149443 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.6866. Min Act: -0.1700
Data Index: 3911267 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.6866. Min Act: -0.1700
Data Index: 7213756 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.6553. Min Act: -0.1700
Data Index: 4665784 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.6241. Min Act: -0.1700
Data Index: 3535450 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.6241. Min Act: -0.1700
Data Index: 8676262 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.6241. Min Act: -0.1700
Data Index: 4505943 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.6241. Min Act: -0.1700
Data Index: 7018746 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0928. Min Range: -6.0928
Max Act: 5.5928. Min Act: -0.1700
Data Index: 1395842 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19