Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1837 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.6775. Min Act: -0.1700
Data Index: 3960270 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.6455. Min Act: -0.1700
Data Index: 6910211 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.6775. Min Act: -0.1700
Data Index: 2023097 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5973. Min Act: -0.1700
Data Index: 6217041 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5811. Min Act: -0.1700
Data Index: 4074060 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.6294. Min Act: -0.1700
Data Index: 882789 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5973. Min Act: -0.1700
Data Index: 6685790 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5811. Min Act: -0.1700
Data Index: 3408010 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5811. Min Act: -0.1700
Data Index: 5874476 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5811. Min Act: -0.1700
Data Index: 4840228 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5811. Min Act: -0.1700
Data Index: 8288112 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5650. Min Act: -0.1700
Data Index: 7256379 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5489. Min Act: -0.1700
Data Index: 6811441 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5489. Min Act: -0.1700
Data Index: 590968 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5489. Min Act: -0.1700
Data Index: 2862244 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5489. Min Act: -0.1700
Data Index: 4701881 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5166. Min Act: -0.1700
Data Index: 8607620 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5327. Min Act: -0.1700
Data Index: 5340365 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5004. Min Act: -0.1700
Data Index: 744135 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6775. Min Range: -2.6775
Max Act: 2.5166. Min Act: -0.1700
Data Index: 4882346 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19