Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 115 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.9630. Min Act: -0.1700
Data Index: 655792 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.9318. Min Act: -0.1700
Data Index: 3902284 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.9005. Min Act: -0.1700
Data Index: 5600037 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.9005. Min Act: -0.1700
Data Index: 2502343 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.8380. Min Act: -0.1700
Data Index: 4782320 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.8380. Min Act: -0.1700
Data Index: 5364078 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.7443. Min Act: -0.1700
Data Index: 5705831 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.7443. Min Act: -0.1700
Data Index: 5150643 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.6818. Min Act: -0.1700
Data Index: 8236550 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.6193. Min Act: -0.1700
Data Index: 8634145 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.6505. Min Act: -0.1700
Data Index: 865917 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.6193. Min Act: -0.1700
Data Index: 8725877 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.6505. Min Act: -0.1700
Data Index: 7621437 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.5880. Min Act: -0.1700
Data Index: 8415698 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.5880. Min Act: -0.1700
Data Index: 1517800 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.5568. Min Act: -0.1700
Data Index: 3607753 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.5568. Min Act: -0.1700
Data Index: 7076375 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.5568. Min Act: -0.1700
Data Index: 8712414 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.5568. Min Act: -0.1700
Data Index: 1265763 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9630. Min Range: -6.9630
Max Act: 6.5568. Min Act: -0.1700
Data Index: 7503221 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19