Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2949 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.5089. Min Act: -0.1700
Data Index: 2294021 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.2277. Min Act: -0.1700
Data Index: 5756923 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.1339. Min Act: -0.1700
Data Index: 1586182 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.0714. Min Act: -0.1700
Data Index: 970166 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.9464. Min Act: -0.1700
Data Index: 832522 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.8839. Min Act: -0.1700
Data Index: 4704978 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.8839. Min Act: -0.1700
Data Index: 2371418 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.8839. Min Act: -0.1700
Data Index: 3742050 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.8839. Min Act: -0.1700
Data Index: 6154747 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.8527. Min Act: -0.1700
Data Index: 5101412 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.8214. Min Act: -0.1700
Data Index: 6067585 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.8214. Min Act: -0.1700
Data Index: 2892681 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.8214. Min Act: -0.1700
Data Index: 1622731 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.8527. Min Act: -0.1700
Data Index: 223698 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.7902. Min Act: -0.1700
Data Index: 4797731 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.7902. Min Act: -0.1700
Data Index: 4675991 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.8214. Min Act: -0.1700
Data Index: 4696771 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.7902. Min Act: -0.1700
Data Index: 3932394 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.7277. Min Act: -0.1700
Data Index: 6929347 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5089. Min Range: -5.5089
Max Act: 4.6964. Min Act: -0.1700
Data Index: 3756941 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19