Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2590 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.8639. Min Act: -0.1700
Data Index: 8651249 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.8124. Min Act: -0.1694
Data Index: 8638384 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.7952. Min Act: -0.1700
Data Index: 1529457 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.7694. Min Act: -0.1699
Data Index: 1407163 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.7607. Min Act: -0.1694
Data Index: 6237856 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.7521. Min Act: -0.1700
Data Index: 2893991 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.7348. Min Act: -0.1700
Data Index: 5657473 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.7435. Min Act: -0.1700
Data Index: 1650901 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.7435. Min Act: -0.1699
Data Index: 2774124 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.7435. Min Act: -0.1699
Data Index: 6626290 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.7262. Min Act: -0.1700
Data Index: 7487049 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.7262. Min Act: -0.1700
Data Index: 4066750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.7348. Min Act: -0.1700
Data Index: 3628723 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.7262. Min Act: -0.1700
Data Index: 1101409 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.7002. Min Act: -0.1700
Data Index: 7075342 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.6915. Min Act: -0.1700
Data Index: 705145 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.6915. Min Act: -0.1699
Data Index: 5252957 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.7002. Min Act: -0.1700
Data Index: 3336608 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.6915. Min Act: -0.1700
Data Index: 1301041 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8639. Min Range: -1.8639
Max Act: 1.6915. Min Act: -0.1700
Data Index: 7188721 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19