Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6221 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.9135. Min Act: -0.1700
Data Index: 3945326 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.9135. Min Act: -0.1700
Data Index: 3945338 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.9135. Min Act: -0.1700
Data Index: 723759 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.7885. Min Act: -0.1700
Data Index: 7041475 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.7260. Min Act: -0.1700
Data Index: 3134398 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.7885. Min Act: -0.1700
Data Index: 3119159 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.6010. Min Act: -0.1700
Data Index: 273961 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.6635. Min Act: -0.1700
Data Index: 1812713 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.5385. Min Act: -0.1700
Data Index: 1528710 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.6010. Min Act: -0.1700
Data Index: 4075670 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.6635. Min Act: -0.1700
Data Index: 7479170 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.6010. Min Act: -0.1700
Data Index: 528622 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.5385. Min Act: -0.1700
Data Index: 3820042 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.4760. Min Act: -0.1700
Data Index: 5346407 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.4760. Min Act: -0.1700
Data Index: 1435976 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.4135. Min Act: -0.1700
Data Index: 4245178 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.4135. Min Act: -0.1700
Data Index: 3484519 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.3510. Min Act: -0.1700
Data Index: 2992944 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.3510. Min Act: -0.1700
Data Index: 878873 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9135. Min Range: -9.9135
Max Act: 9.3510. Min Act: -0.1700
Data Index: 3884840 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19