Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 460 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.8859. Min Act: -0.1700
Data Index: 2118675 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.8383. Min Act: -0.1700
Data Index: 620954 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.8383. Min Act: -0.1700
Data Index: 4906277 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.8224. Min Act: -0.1700
Data Index: 6932185 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.8383. Min Act: -0.1700
Data Index: 1702118 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.8383. Min Act: -0.1700
Data Index: 4692566 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.8383. Min Act: -0.1700
Data Index: 4943043 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.8224. Min Act: -0.1700
Data Index: 4470351 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.8224. Min Act: -0.1700
Data Index: 981272 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.8383. Min Act: -0.1700
Data Index: 7916429 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.8065. Min Act: -0.1700
Data Index: 6470611 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.7905. Min Act: -0.1700
Data Index: 4158595 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.7905. Min Act: -0.1700
Data Index: 4720136 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.7746. Min Act: -0.1700
Data Index: 7880623 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.7746. Min Act: -0.1700
Data Index: 483920 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.7905. Min Act: -0.1700
Data Index: 6520428 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.7586. Min Act: -0.1700
Data Index: 5651476 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.7427. Min Act: -0.1700
Data Index: 4618164 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.7427. Min Act: -0.1700
Data Index: 4608292 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8859. Min Range: -2.8859
Max Act: 2.7267. Min Act: -0.1700
Data Index: 5599958 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19