Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1645 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.4389. Min Act: -0.1700
Data Index: 7656173 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.4702. Min Act: -0.1700
Data Index: 7938858 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.4077. Min Act: -0.1700
Data Index: 2770036 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.3764. Min Act: -0.1700
Data Index: 4313008 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.3452. Min Act: -0.1700
Data Index: 2543569 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.3452. Min Act: -0.1700
Data Index: 4473648 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.3139. Min Act: -0.1700
Data Index: 8243240 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.3139. Min Act: -0.1700
Data Index: 5454126 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.2827. Min Act: -0.1700
Data Index: 614625 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.3139. Min Act: -0.1700
Data Index: 8536512 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.3139. Min Act: -0.1700
Data Index: 7597980 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.2827. Min Act: -0.1700
Data Index: 1204930 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.3139. Min Act: -0.1700
Data Index: 7791646 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.3139. Min Act: -0.1700
Data Index: 4211242 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.2827. Min Act: -0.1700
Data Index: 82758 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.2827. Min Act: -0.1700
Data Index: 3226530 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.2827. Min Act: -0.1700
Data Index: 639956 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.2514. Min Act: -0.1700
Data Index: 5810435 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.2827. Min Act: -0.1700
Data Index: 507310 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.2827. Min Act: -0.1700
Data Index: 6513163 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19