Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3434 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0260. Min Range: -6.0260
Max Act: 6.0260. Min Act: -0.1700
Data Index: 5275387 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.8385. Min Act: -0.1700
Data Index: 5275394 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.8385. Min Act: -0.1700
Data Index: 3772542 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.8385. Min Act: -0.1700
Data Index: 7369500 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.7448. Min Act: -0.1700
Data Index: 4867850 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.7448. Min Act: -0.1700
Data Index: 6620779 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.8073. Min Act: -0.1700
Data Index: 5275401 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.7448. Min Act: -0.1700
Data Index: 2795971 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.5573. Min Act: -0.1700
Data Index: 6238909 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.6510. Min Act: -0.1700
Data Index: 5982733 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.6198. Min Act: -0.1700
Data Index: 7951329 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.6823. Min Act: -0.1700
Data Index: 259774 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.6198. Min Act: -0.1700
Data Index: 5275386 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.6510. Min Act: -0.1700
Data Index: 923025 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.5573. Min Act: -0.1700
Data Index: 5489958 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.6198. Min Act: -0.1700
Data Index: 6031085 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.5573. Min Act: -0.1700
Data Index: 6283441 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.5885. Min Act: -0.1700
Data Index: 8251850 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.5885. Min Act: -0.1700
Data Index: 3988040 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0260. Min Range: -6.0260
Max Act: 5.5885. Min Act: -0.1700
Data Index: 2842894 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19