Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2484 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.8556. Min Act: -0.1700
Data Index: 2250151 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.8384. Min Act: -0.1700
Data Index: 3596119 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.8213. Min Act: -0.1700
Data Index: 3353495 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.8213. Min Act: -0.1700
Data Index: 3224036 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.8213. Min Act: -0.1700
Data Index: 3353485 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.7869. Min Act: -0.1700
Data Index: 3596144 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.7869. Min Act: -0.1700
Data Index: 3596142 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.7869. Min Act: -0.1700
Data Index: 3596126 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.7869. Min Act: -0.1700
Data Index: 3596146 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.7869. Min Act: -0.1700
Data Index: 3596124 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.7869. Min Act: -0.1700
Data Index: 2640086 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.7869. Min Act: -0.1700
Data Index: 3596125 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.7869. Min Act: -0.1700
Data Index: 3596129 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.7869. Min Act: -0.1700
Data Index: 3596127 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.7696. Min Act: -0.1700
Data Index: 3596121 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.7869. Min Act: -0.1700
Data Index: 3596143 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.7869. Min Act: -0.1700
Data Index: 3596128 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.7696. Min Act: -0.1700
Data Index: 3596120 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.7869. Min Act: -0.1700
Data Index: 3596123 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8556. Min Range: -1.8556
Max Act: 1.7869. Min Act: -0.1700
Data Index: 3596141 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19