Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2219 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.3750. Min Act: -0.1700
Data Index: 2925250 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.3594. Min Act: -0.1700
Data Index: 5324374 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.1709. Min Act: -0.1700
Data Index: 8832801 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.1709. Min Act: -0.1700
Data Index: 4110468 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.1394. Min Act: -0.1700
Data Index: 6755189 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.1394. Min Act: -0.1700
Data Index: 5828843 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.1394. Min Act: -0.1700
Data Index: 93291 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.1394. Min Act: -0.1700
Data Index: 4926704 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.1236. Min Act: -0.1700
Data Index: 722961 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.0921. Min Act: -0.1700
Data Index: 172010 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.0921. Min Act: -0.1700
Data Index: 4376016 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.1079. Min Act: -0.1700
Data Index: 2452348 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.0921. Min Act: -0.1700
Data Index: 1459561 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.0921. Min Act: -0.1700
Data Index: 8073795 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.0921. Min Act: -0.1700
Data Index: 2575056 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.0290. Min Act: -0.1700
Data Index: 2779946 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.0763. Min Act: -0.1700
Data Index: 5324373 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.0606. Min Act: -0.1700
Data Index: 2894625 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.0448. Min Act: -0.1700
Data Index: 6511994 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3750. Min Range: -3.3750
Max Act: 3.0763. Min Act: -0.1700
Data Index: 3999170 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19