Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3708 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.5088. Min Act: -0.1700
Data Index: 4071391 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.5088. Min Act: -0.1700
Data Index: 6549639 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.4463. Min Act: -0.1700
Data Index: 6214903 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.4463. Min Act: -0.1700
Data Index: 338242 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.4463. Min Act: -0.1700
Data Index: 3136357 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.4463. Min Act: -0.1700
Data Index: 5581259 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.4463. Min Act: -0.1700
Data Index: 2856714 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.4151. Min Act: -0.1700
Data Index: 1707360 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.3838. Min Act: -0.1700
Data Index: 2353027 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.3838. Min Act: -0.1700
Data Index: 911400 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.3838. Min Act: -0.1700
Data Index: 6981987 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.3838. Min Act: -0.1699
Data Index: 5847068 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.3526. Min Act: -0.1700
Data Index: 3440932 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.3838. Min Act: -0.1700
Data Index: 5026696 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.3838. Min Act: -0.1700
Data Index: 1170368 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.3838. Min Act: -0.1700
Data Index: 2604351 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.3838. Min Act: -0.1700
Data Index: 654924 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.3838. Min Act: -0.1700
Data Index: 3041805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.3838. Min Act: -0.1700
Data Index: 943212 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5088. Min Range: -5.5088
Max Act: 5.3838. Min Act: -0.1700
Data Index: 2086 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19