Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5382 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5039. Min Range: -7.5039
Max Act: 7.5039. Min Act: -0.1700
Data Index: 5195666 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5039. Min Range: -7.5039
Max Act: 7.1914. Min Act: -0.1700
Data Index: 253666 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5039. Min Range: -7.5039
Max Act: 7.1601. Min Act: -0.1700
Data Index: 6989393 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5039. Min Range: -7.5039
Max Act: 7.0976. Min Act: -0.1700
Data Index: 6843946 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5039. Min Range: -7.5039
Max Act: 7.0976. Min Act: -0.1700
Data Index: 1105530 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5039. Min Range: -7.5039
Max Act: 7.0351. Min Act: -0.1700
Data Index: 1646939 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5039. Min Range: -7.5039
Max Act: 7.0351. Min Act: -0.1700
Data Index: 1605702 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5039. Min Range: -7.5039
Max Act: 7.0039. Min Act: -0.1700
Data Index: 4949559 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5039. Min Range: -7.5039
Max Act: 6.9726. Min Act: -0.1700
Data Index: 5795576 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5039. Min Range: -7.5039
Max Act: 6.9101. Min Act: -0.1700
Data Index: 7294986 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5039. Min Range: -7.5039
Max Act: 6.9414. Min Act: -0.1700
Data Index: 7084974 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5039. Min Range: -7.5039
Max Act: 6.9414. Min Act: -0.1700
Data Index: 3399226 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5039. Min Range: -7.5039
Max Act: 6.9726. Min Act: -0.1700
Data Index: 3396955 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5039. Min Range: -7.5039
Max Act: 6.9101. Min Act: -0.1700
Data Index: 1570224 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5039. Min Range: -7.5039
Max Act: 6.8789. Min Act: -0.1700
Data Index: 4413739 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5039. Min Range: -7.5039
Max Act: 6.8476. Min Act: -0.1700
Data Index: 8805221 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5039. Min Range: -7.5039
Max Act: 6.7851. Min Act: -0.1700
Data Index: 1520908 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5039. Min Range: -7.5039
Max Act: 6.7851. Min Act: -0.1700
Data Index: 4685566 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5039. Min Range: -7.5039
Max Act: 6.8164. Min Act: -0.1700
Data Index: 8705673 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5039. Min Range: -7.5039
Max Act: 6.7851. Min Act: -0.1700
Data Index: 2447662 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19