Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2760 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0297. Min Range: -6.0297
Max Act: 6.0297. Min Act: -0.1700
Data Index: 8165582 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.9984. Min Act: -0.1700
Data Index: 379299 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.9672. Min Act: -0.1700
Data Index: 7235623 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.8422. Min Act: -0.1700
Data Index: 7425117 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.7172. Min Act: -0.1700
Data Index: 732136 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.7172. Min Act: -0.1700
Data Index: 7140470 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.7172. Min Act: -0.1700
Data Index: 4057797 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.6547. Min Act: -0.1700
Data Index: 6439604 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.5922. Min Act: -0.1700
Data Index: 4752421 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.5297. Min Act: -0.1700
Data Index: 3720783 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.5609. Min Act: -0.1700
Data Index: 8354286 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4984. Min Act: -0.1700
Data Index: 5194585 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4984. Min Act: -0.1700
Data Index: 1362270 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4672. Min Act: -0.1700
Data Index: 8305818 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4672. Min Act: -0.1700
Data Index: 1577003 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4359. Min Act: -0.1700
Data Index: 8291051 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4359. Min Act: -0.1700
Data Index: 5910600 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4047. Min Act: -0.1700
Data Index: 3133990 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4359. Min Act: -0.1700
Data Index: 1824507 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4359. Min Act: -0.1700
Data Index: 1551284 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19