Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 567 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.4001. Min Act: -0.1700
Data Index: 4003218 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.3060. Min Act: -0.1700
Data Index: 4285510 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.2903. Min Act: -0.1700
Data Index: 4917124 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.2903. Min Act: -0.1700
Data Index: 2254091 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.2903. Min Act: -0.1700
Data Index: 3932955 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.3060. Min Act: -0.1700
Data Index: 7584452 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.2432. Min Act: -0.1700
Data Index: 1836524 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.1960. Min Act: -0.1700
Data Index: 3441136 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.2118. Min Act: -0.1700
Data Index: 6508080 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.2118. Min Act: -0.1700
Data Index: 8169359 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.2118. Min Act: -0.1700
Data Index: 7181332 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.1803. Min Act: -0.1700
Data Index: 5575303 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.2432. Min Act: -0.1700
Data Index: 2692225 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.1646. Min Act: -0.1700
Data Index: 8513583 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.2118. Min Act: -0.1700
Data Index: 5152718 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.1331. Min Act: -0.1700
Data Index: 7557324 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.1646. Min Act: -0.1700
Data Index: 2198275 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.2118. Min Act: -0.1700
Data Index: 2028220 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.2118. Min Act: -0.1700
Data Index: 5810077 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4001. Min Range: -3.4001
Max Act: 3.1960. Min Act: -0.1700
Data Index: 6959391 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19