Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1377 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.6668. Min Act: -0.1700
Data Index: 6768531 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.5731. Min Act: -0.1700
Data Index: 141123 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.5106. Min Act: -0.1700
Data Index: 5051493 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.5106. Min Act: -0.1700
Data Index: 96195 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.4793. Min Act: -0.1700
Data Index: 3964968 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.4481. Min Act: -0.1700
Data Index: 2777017 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.4481. Min Act: -0.1700
Data Index: 2744324 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.4481. Min Act: -0.1700
Data Index: 3334041 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.4481. Min Act: -0.1700
Data Index: 401275 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.4168. Min Act: -0.1700
Data Index: 552072 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.4168. Min Act: -0.1700
Data Index: 8328181 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.3856. Min Act: -0.1700
Data Index: 850243 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.4168. Min Act: -0.1700
Data Index: 7581320 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.4481. Min Act: -0.1700
Data Index: 7032905 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.3856. Min Act: -0.1700
Data Index: 6848762 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.4168. Min Act: -0.1700
Data Index: 4081180 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.3856. Min Act: -0.1700
Data Index: 4231574 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.3543. Min Act: -0.1700
Data Index: 4103005 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.3543. Min Act: -0.1700
Data Index: 1493948 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6668. Min Range: -4.6668
Max Act: 4.3856. Min Act: -0.1700
Data Index: 3494205 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19