Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1770 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.5684. Min Act: -0.1700
Data Index: 8668993 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.5361. Min Act: -0.1700
Data Index: 4726800 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.4876. Min Act: -0.1700
Data Index: 7745131 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.5199. Min Act: -0.1700
Data Index: 7745130 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.4713. Min Act: -0.1700
Data Index: 4726801 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.3408. Min Act: -0.1700
Data Index: 4348039 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.4062. Min Act: -0.1700
Data Index: 6366101 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.3736. Min Act: -0.1700
Data Index: 5806170 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.3572. Min Act: -0.1700
Data Index: 3057163 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.3736. Min Act: -0.1700
Data Index: 399651 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.3080. Min Act: -0.1700
Data Index: 6949419 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.3736. Min Act: -0.1700
Data Index: 2393723 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.3572. Min Act: -0.1700
Data Index: 7739973 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.2586. Min Act: -0.1700
Data Index: 2719553 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.3408. Min Act: -0.1700
Data Index: 6544984 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.3244. Min Act: -0.1700
Data Index: 2238809 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.3736. Min Act: -0.1700
Data Index: 6286052 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.3080. Min Act: -0.1700
Data Index: 2409114 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.2586. Min Act: -0.1700
Data Index: 492830 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5684. Min Range: -2.5684
Max Act: 2.3080. Min Act: -0.1700
Data Index: 6825054 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19