Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3157 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1337. Min Range: -5.1337
Max Act: 5.1337. Min Act: -0.1700
Data Index: 1397512 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1337. Min Range: -5.1337
Max Act: 5.0400. Min Act: -0.1700
Data Index: 8056341 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1337. Min Range: -5.1337
Max Act: 5.0087. Min Act: -0.1700
Data Index: 8288439 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1337. Min Range: -5.1337
Max Act: 5.0087. Min Act: -0.1700
Data Index: 279188 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.9775. Min Act: -0.1700
Data Index: 3437852 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.9462. Min Act: -0.1700
Data Index: 1920684 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.9150. Min Act: -0.1700
Data Index: 844800 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.9150. Min Act: -0.1700
Data Index: 2441451 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.9462. Min Act: -0.1700
Data Index: 299180 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.8837. Min Act: -0.1700
Data Index: 5214594 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.8837. Min Act: -0.1700
Data Index: 6735331 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.9150. Min Act: -0.1700
Data Index: 4572358 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.8525. Min Act: -0.1700
Data Index: 1403646 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.8212. Min Act: -0.1700
Data Index: 4147098 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.8525. Min Act: -0.1700
Data Index: 5108088 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.8212. Min Act: -0.1700
Data Index: 7610972 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.8212. Min Act: -0.1700
Data Index: 6213766 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.8212. Min Act: -0.1700
Data Index: 2962067 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.7900. Min Act: -0.1700
Data Index: 7373265 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1337. Min Range: -5.1337
Max Act: 4.8212. Min Act: -0.1700
Data Index: 6177405 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19