Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1150 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3707. Min Range: -8.3707
Max Act: 8.3707. Min Act: -0.1700
Data Index: 8461061 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3707. Min Range: -8.3707
Max Act: 8.0270. Min Act: -0.1700
Data Index: 179995 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.7457. Min Act: -0.1700
Data Index: 454663 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.6832. Min Act: -0.1700
Data Index: 5040003 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.7145. Min Act: -0.1700
Data Index: 2660208 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.7145. Min Act: -0.1700
Data Index: 1475544 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.6832. Min Act: -0.1700
Data Index: 4258626 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.6207. Min Act: -0.1700
Data Index: 2550500 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.5895. Min Act: -0.1700
Data Index: 6841343 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.6207. Min Act: -0.1700
Data Index: 3805090 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.5582. Min Act: -0.1700
Data Index: 4775568 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.5270. Min Act: -0.1700
Data Index: 3105736 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.5270. Min Act: -0.1700
Data Index: 7839811 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.4957. Min Act: -0.1700
Data Index: 2613639 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.4957. Min Act: -0.1700
Data Index: 7709228 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.4957. Min Act: -0.1700
Data Index: 316878 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.4645. Min Act: -0.1700
Data Index: 1949570 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.4645. Min Act: -0.1700
Data Index: 7402030 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.4957. Min Act: -0.1700
Data Index: 3497612 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3707. Min Range: -8.3707
Max Act: 7.4645. Min Act: -0.1700
Data Index: 1185028 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19