Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3755 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.9711. Min Act: -0.1700
Data Index: 2328254 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.9555. Min Act: -0.1700
Data Index: 4569557 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.9398. Min Act: -0.1700
Data Index: 6770710 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.8929. Min Act: -0.1700
Data Index: 1031795 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.8460. Min Act: -0.1700
Data Index: 6532998 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.8773. Min Act: -0.1700
Data Index: 7476744 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.8617. Min Act: -0.1700
Data Index: 4732860 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.8304. Min Act: -0.1700
Data Index: 1242373 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.8773. Min Act: -0.1700
Data Index: 898416 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.7835. Min Act: -0.1700
Data Index: 8293235 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.7991. Min Act: -0.1700
Data Index: 5879839 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.7991. Min Act: -0.1700
Data Index: 2627448 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.7835. Min Act: -0.1700
Data Index: 3834757 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.7679. Min Act: -0.1700
Data Index: 7321473 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.7366. Min Act: -0.1700
Data Index: 548036 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.7366. Min Act: -0.1700
Data Index: 6802392 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.7053. Min Act: -0.1700
Data Index: 1335411 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.7366. Min Act: -0.1700
Data Index: 7653347 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.7209. Min Act: -0.1700
Data Index: 5661968 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9711. Min Range: -3.9711
Max Act: 3.7053. Min Act: -0.1700
Data Index: 7636298 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19