Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4623 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.1683. Min Act: -0.1700
Data Index: 6212571 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.1526. Min Act: -0.1700
Data Index: 2669882 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.1053. Min Act: -0.1700
Data Index: 607585 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.1053. Min Act: -0.1700
Data Index: 4897911 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.1053. Min Act: -0.1700
Data Index: 7754761 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.0580. Min Act: -0.1700
Data Index: 3379641 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.0580. Min Act: -0.1700
Data Index: 3500170 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.0580. Min Act: -0.1700
Data Index: 7649703 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.0422. Min Act: -0.1700
Data Index: 1188664 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.0422. Min Act: -0.1700
Data Index: 3413239 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.0264. Min Act: -0.1700
Data Index: 2476716 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.0106. Min Act: -0.1700
Data Index: 3632739 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.0264. Min Act: -0.1700
Data Index: 4022833 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.0264. Min Act: -0.1700
Data Index: 798723 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.0264. Min Act: -0.1700
Data Index: 7612288 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.0106. Min Act: -0.1700
Data Index: 5174177 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.0106. Min Act: -0.1700
Data Index: 5230180 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.0106. Min Act: -0.1700
Data Index: 552755 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.0106. Min Act: -0.1700
Data Index: 5415242 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1683. Min Range: -3.1683
Max Act: 3.0106. Min Act: -0.1700
Data Index: 5832739 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19