Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3019 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.7381. Min Act: -0.1700
Data Index: 2453128 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.7069. Min Act: -0.1700
Data Index: 4282363 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.6756. Min Act: -0.1700
Data Index: 2453127 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.6756. Min Act: -0.1700
Data Index: 2453126 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.6444. Min Act: -0.1700
Data Index: 2440871 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.6444. Min Act: -0.1700
Data Index: 7011710 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.6131. Min Act: -0.1700
Data Index: 1803742 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.6131. Min Act: -0.1700
Data Index: 7011709 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5819. Min Act: -0.1700
Data Index: 8716874 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5819. Min Act: -0.1700
Data Index: 5276599 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5819. Min Act: -0.1700
Data Index: 5340757 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5506. Min Act: -0.1700
Data Index: 6673283 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5506. Min Act: -0.1700
Data Index: 4150287 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5506. Min Act: -0.1700
Data Index: 5912896 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5506. Min Act: -0.1700
Data Index: 4865469 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5506. Min Act: -0.1700
Data Index: 3450546 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5506. Min Act: -0.1700
Data Index: 5799416 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5194. Min Act: -0.1700
Data Index: 1484733 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.4881. Min Act: -0.1700
Data Index: 3760239 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5194. Min Act: -0.1700
Data Index: 339578 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19