Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4036 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.9089. Min Act: -0.1700
Data Index: 4782985 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.6902. Min Act: -0.1700
Data Index: 2161204 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.6277. Min Act: -0.1700
Data Index: 3588149 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.5652. Min Act: -0.1700
Data Index: 3497162 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.4714. Min Act: -0.1700
Data Index: 8472298 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.4402. Min Act: -0.1700
Data Index: 2755255 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.3777. Min Act: -0.1700
Data Index: 3870482 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.3777. Min Act: -0.1700
Data Index: 7843403 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.2527. Min Act: -0.1700
Data Index: 199534 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.2214. Min Act: -0.1700
Data Index: 1228215 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.2214. Min Act: -0.1700
Data Index: 2569769 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.2214. Min Act: -0.1700
Data Index: 4802560 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.2527. Min Act: -0.1700
Data Index: 1067945 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.2214. Min Act: -0.1700
Data Index: 6041180 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.1902. Min Act: -0.1700
Data Index: 3412616 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.1902. Min Act: -0.1700
Data Index: 5907342 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.1902. Min Act: -0.1700
Data Index: 7414949 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.1902. Min Act: -0.1700
Data Index: 6097698 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.1902. Min Act: -0.1700
Data Index: 1291597 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9089. Min Range: -6.9089
Max Act: 6.1589. Min Act: -0.1700
Data Index: 3775933 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19