Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1380 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.3952. Min Act: -0.1700
Data Index: 6724625 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.3327. Min Act: -0.1700
Data Index: 6504835 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.3014. Min Act: -0.1700
Data Index: 2626282 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.3014. Min Act: -0.1700
Data Index: 8625134 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.2702. Min Act: -0.1700
Data Index: 4228668 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.3014. Min Act: -0.1700
Data Index: 338270 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.2702. Min Act: -0.1700
Data Index: 156883 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.2389. Min Act: -0.1700
Data Index: 7529577 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.2389. Min Act: -0.1700
Data Index: 4180026 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.2389. Min Act: -0.1700
Data Index: 4789431 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.2389. Min Act: -0.1700
Data Index: 6786759 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.2389. Min Act: -0.1700
Data Index: 984935 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.2389. Min Act: -0.1700
Data Index: 421049 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.2389. Min Act: -0.1700
Data Index: 1295033 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.2077. Min Act: -0.1700
Data Index: 4752261 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.2077. Min Act: -0.1700
Data Index: 3335500 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.2077. Min Act: -0.1700
Data Index: 569862 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.2077. Min Act: -0.1700
Data Index: 3387490 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.2077. Min Act: -0.1700
Data Index: 3851690 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3952. Min Range: -4.3952
Max Act: 4.2077. Min Act: -0.1700
Data Index: 542340 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19