Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1626 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.3095. Min Act: -0.1700
Data Index: 8303503 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.2765. Min Act: -0.1700
Data Index: 2669844 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.2765. Min Act: -0.1700
Data Index: 4259506 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.2270. Min Act: -0.1700
Data Index: 5465859 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.2104. Min Act: -0.1700
Data Index: 7581626 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.1938. Min Act: -0.1700
Data Index: 7195991 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.1772. Min Act: -0.1700
Data Index: 1012925 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.1606. Min Act: -0.1700
Data Index: 2450388 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.1439. Min Act: -0.1700
Data Index: 8170466 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.1272. Min Act: -0.1700
Data Index: 5244862 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.1272. Min Act: -0.1700
Data Index: 6122191 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.1272. Min Act: -0.1700
Data Index: 4277703 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.1272. Min Act: -0.1700
Data Index: 6334451 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.1272. Min Act: -0.1700
Data Index: 4933568 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.1105. Min Act: -0.1700
Data Index: 72788 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.1272. Min Act: -0.1697
Data Index: 3644777 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.0937. Min Act: -0.1700
Data Index: 750039 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.0937. Min Act: -0.1700
Data Index: 225837 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.0937. Min Act: -0.1700
Data Index: 6491139 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3095. Min Range: -2.3095
Max Act: 2.1105. Min Act: -0.1700
Data Index: 1704953 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19