Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.8036. Min Act: -0.1700
Data Index: 8761969 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.7238. Min Act: -0.1700
Data Index: 4003584 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.7078. Min Act: -0.1700
Data Index: 8190423 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.6918. Min Act: -0.1700
Data Index: 83284 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.7078. Min Act: -0.1700
Data Index: 2069480 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.6758. Min Act: -0.1700
Data Index: 6041798 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.6758. Min Act: -0.1700
Data Index: 1147221 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.6598. Min Act: -0.1700
Data Index: 5757668 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.6598. Min Act: -0.1700
Data Index: 1739864 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.6758. Min Act: -0.1700
Data Index: 8643421 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.6276. Min Act: -0.1700
Data Index: 4330730 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.6437. Min Act: -0.1700
Data Index: 8655811 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.6437. Min Act: -0.1700
Data Index: 6645756 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.6276. Min Act: -0.1700
Data Index: 8473247 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.6116. Min Act: -0.1700
Data Index: 8133691 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.5794. Min Act: -0.1700
Data Index: 5506788 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.6116. Min Act: -0.1700
Data Index: 1770460 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.6116. Min Act: -0.1700
Data Index: 7585613 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.5794. Min Act: -0.1700
Data Index: 4055131 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8036. Min Range: -2.8036
Max Act: 2.5794. Min Act: -0.1700
Data Index: 85466 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19