Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3286 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.6811. Min Act: -0.1700
Data Index: 6791189 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.6186. Min Act: -0.1700
Data Index: 1979537 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.5874. Min Act: -0.1700
Data Index: 7904581 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.5561. Min Act: -0.1700
Data Index: 3842222 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.5249. Min Act: -0.1700
Data Index: 1101682 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.4936. Min Act: -0.1700
Data Index: 2729028 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.5249. Min Act: -0.1700
Data Index: 1471998 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.4936. Min Act: -0.1700
Data Index: 2603160 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.4936. Min Act: -0.1700
Data Index: 3958922 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.4936. Min Act: -0.1700
Data Index: 839802 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.4936. Min Act: -0.1700
Data Index: 4938814 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.4624. Min Act: -0.1700
Data Index: 4057331 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.4624. Min Act: -0.1700
Data Index: 3411175 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.4624. Min Act: -0.1700
Data Index: 419470 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.4624. Min Act: -0.1700
Data Index: 6468060 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.4624. Min Act: -0.1700
Data Index: 4175993 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.4624. Min Act: -0.1700
Data Index: 5992728 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.4624. Min Act: -0.1700
Data Index: 1591962 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.4311. Min Act: -0.1700
Data Index: 435198 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6811. Min Range: -4.6811
Max Act: 4.4311. Min Act: -0.1700
Data Index: 996857 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19