Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1526 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7166. Min Range: -5.7166
Max Act: 5.7166. Min Act: -0.1700
Data Index: 123308 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7166. Min Range: -5.7166
Max Act: 5.3416. Min Act: -0.1700
Data Index: 1781843 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7166. Min Range: -5.7166
Max Act: 5.3728. Min Act: -0.1700
Data Index: 4020048 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7166. Min Range: -5.7166
Max Act: 5.2478. Min Act: -0.1700
Data Index: 3574479 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7166. Min Range: -5.7166
Max Act: 5.2166. Min Act: -0.1697
Data Index: 4933429 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7166. Min Range: -5.7166
Max Act: 5.1853. Min Act: -0.1700
Data Index: 6829593 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7166. Min Range: -5.7166
Max Act: 5.1228. Min Act: -0.1700
Data Index: 6502082 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7166. Min Range: -5.7166
Max Act: 5.1228. Min Act: -0.1700
Data Index: 5270614 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7166. Min Range: -5.7166
Max Act: 5.0916. Min Act: -0.1700
Data Index: 1006218 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7166. Min Range: -5.7166
Max Act: 5.0603. Min Act: -0.1700
Data Index: 7998329 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7166. Min Range: -5.7166
Max Act: 5.0603. Min Act: -0.1700
Data Index: 7358458 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7166. Min Range: -5.7166
Max Act: 4.9978. Min Act: -0.1700
Data Index: 5079237 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7166. Min Range: -5.7166
Max Act: 4.9978. Min Act: -0.1700
Data Index: 228808 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7166. Min Range: -5.7166
Max Act: 4.9978. Min Act: -0.1700
Data Index: 899862 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7166. Min Range: -5.7166
Max Act: 4.9978. Min Act: -0.1700
Data Index: 4514242 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7166. Min Range: -5.7166
Max Act: 4.9978. Min Act: -0.1700
Data Index: 1987890 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7166. Min Range: -5.7166
Max Act: 4.9353. Min Act: -0.1700
Data Index: 8304185 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7166. Min Range: -5.7166
Max Act: 4.9353. Min Act: -0.1700
Data Index: 1715965 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7166. Min Range: -5.7166
Max Act: 4.9353. Min Act: -0.1700
Data Index: 146691 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7166. Min Range: -5.7166
Max Act: 4.9353. Min Act: -0.1700
Data Index: 2231578 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19