Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1899 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.9580. Min Act: -0.1681
Data Index: 7571038 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.9424. Min Act: -0.1699
Data Index: 8492832 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.7704. Min Act: -0.1700
Data Index: 643113 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.6609. Min Act: -0.1700
Data Index: 1184740 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.5983. Min Act: -0.1700
Data Index: 3708587 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.6140. Min Act: -0.1617
Data Index: 3565893 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.5983. Min Act: -0.1700
Data Index: 3925250 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.5827. Min Act: -0.1698
Data Index: 6272573 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.5827. Min Act: -0.1698
Data Index: 4171520 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.5514. Min Act: -0.1700
Data Index: 5566441 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.5201. Min Act: -0.1649
Data Index: 5053742 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.5044. Min Act: -0.1700
Data Index: 42923 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.5044. Min Act: -0.1700
Data Index: 3215429 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.5044. Min Act: -0.1700
Data Index: 4439272 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.5044. Min Act: -0.1700
Data Index: 2908460 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.4887. Min Act: -0.1685
Data Index: 7762899 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.4887. Min Act: -0.1254
Data Index: 3680757 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.5044. Min Act: -0.1620
Data Index: 8704568 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.4731. Min Act: -0.1700
Data Index: 8375525 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9580. Min Range: -3.9580
Max Act: 3.4731. Min Act: -0.1696
Data Index: 3123097 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19