Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2883 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2025. Min Range: -6.2025
Max Act: 6.2025. Min Act: -0.1700
Data Index: 6150460 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2025. Min Range: -6.2025
Max Act: 6.0150. Min Act: -0.1700
Data Index: 7081528 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.9212. Min Act: -0.1700
Data Index: 6150470 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.9212. Min Act: -0.1700
Data Index: 8606332 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.8900. Min Act: -0.1700
Data Index: 5517355 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.8900. Min Act: -0.1700
Data Index: 3886547 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7962. Min Act: -0.1700
Data Index: 7115708 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7337. Min Act: -0.1700
Data Index: 2992130 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7962. Min Act: -0.1700
Data Index: 3130326 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.8275. Min Act: -0.1700
Data Index: 897789 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7337. Min Act: -0.1700
Data Index: 6297979 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7337. Min Act: -0.1700
Data Index: 2992133 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7962. Min Act: -0.1700
Data Index: 2460216 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7337. Min Act: -0.1700
Data Index: 3279252 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7337. Min Act: -0.1700
Data Index: 8523997 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7025. Min Act: -0.1700
Data Index: 7343778 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.6712. Min Act: -0.1700
Data Index: 1381575 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7025. Min Act: -0.1700
Data Index: 2722171 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7025. Min Act: -0.1700
Data Index: 161259 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7025. Min Act: -0.1700
Data Index: 5156590 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19