Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1913 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.6049. Min Act: -0.1700
Data Index: 2308710 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.6049. Min Act: -0.1700
Data Index: 2251097 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.5727. Min Act: -0.1700
Data Index: 8769606 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.5565. Min Act: -0.1700
Data Index: 6643556 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.5404. Min Act: -0.1700
Data Index: 6357876 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.5242. Min Act: -0.1700
Data Index: 6853107 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.5081. Min Act: -0.1700
Data Index: 1061327 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.5081. Min Act: -0.1700
Data Index: 4059379 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.4919. Min Act: -0.1700
Data Index: 8694672 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.5081. Min Act: -0.1700
Data Index: 4461171 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.4919. Min Act: -0.1700
Data Index: 7184293 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.4919. Min Act: -0.1700
Data Index: 3485495 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.4756. Min Act: -0.1700
Data Index: 7024413 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.4431. Min Act: -0.1700
Data Index: 4422775 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.4431. Min Act: -0.1700
Data Index: 6357269 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.4431. Min Act: -0.1700
Data Index: 2843403 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.4431. Min Act: -0.1700
Data Index: 4756323 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.4431. Min Act: -0.1700
Data Index: 1787246 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.4269. Min Act: -0.1700
Data Index: 6821357 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6049. Min Range: -2.6049
Max Act: 2.4269. Min Act: -0.1698
Data Index: 7252736 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19