Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 362 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0507. Min Range: -3.0507
Max Act: 3.0507. Min Act: -0.1700
Data Index: 1297907 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9717. Min Act: -0.1700
Data Index: 6690469 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9559. Min Act: -0.1700
Data Index: 3848508 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.9401. Min Act: -0.1700
Data Index: 5467965 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.8925. Min Act: -0.1700
Data Index: 8783374 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.8767. Min Act: -0.1700
Data Index: 5620305 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.8449. Min Act: -0.1700
Data Index: 4044740 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.8131. Min Act: -0.1700
Data Index: 7924716 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.8290. Min Act: -0.1700
Data Index: 8043446 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.8608. Min Act: -0.1700
Data Index: 8358095 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.8131. Min Act: -0.1700
Data Index: 5930787 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.8131. Min Act: -0.1700
Data Index: 8066869 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.8131. Min Act: -0.1700
Data Index: 6732556 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.7812. Min Act: -0.1700
Data Index: 4059494 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.7972. Min Act: -0.1700
Data Index: 3039451 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.7653. Min Act: -0.1700
Data Index: 3472577 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.7653. Min Act: -0.1700
Data Index: 4217828 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.7653. Min Act: -0.1700
Data Index: 837044 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.7812. Min Act: -0.1700
Data Index: 216453 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0507. Min Range: -3.0507
Max Act: 2.7653. Min Act: -0.1700
Data Index: 6116906 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19