Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2053 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.6472. Min Act: -0.1700
Data Index: 1643365 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.4597. Min Act: -0.1700
Data Index: 1118161 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.4284. Min Act: -0.1700
Data Index: 795867 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.3347. Min Act: -0.1700
Data Index: 1173884 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.3972. Min Act: -0.1700
Data Index: 1259441 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.3347. Min Act: -0.1700
Data Index: 1407242 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.3034. Min Act: -0.1700
Data Index: 1601181 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.1159. Min Act: -0.1700
Data Index: 2234352 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.1472. Min Act: -0.1700
Data Index: 202532 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.1472. Min Act: -0.1700
Data Index: 2077367 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.1159. Min Act: -0.1700
Data Index: 733022 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.1159. Min Act: -0.1700
Data Index: 4640117 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.1159. Min Act: -0.1700
Data Index: 617415 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.0847. Min Act: -0.1700
Data Index: 4705661 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.0847. Min Act: -0.1700
Data Index: 4988839 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.0847. Min Act: -0.1700
Data Index: 4526625 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.1159. Min Act: -0.1700
Data Index: 1195557 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.0534. Min Act: -0.1700
Data Index: 2773909 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.0534. Min Act: -0.1700
Data Index: 1012191 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6472. Min Range: -5.6472
Max Act: 5.0847. Min Act: -0.1700
Data Index: 2770563 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19