Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.7965. Min Act: -0.1700
Data Index: 2304945 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.7653. Min Act: -0.1700
Data Index: 8056036 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.7028. Min Act: -0.1700
Data Index: 1448393 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.6090. Min Act: -0.1700
Data Index: 1252345 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.6090. Min Act: -0.1700
Data Index: 2101200 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.6090. Min Act: -0.1700
Data Index: 1145371 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.6090. Min Act: -0.1700
Data Index: 7370640 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.6090. Min Act: -0.1700
Data Index: 4684560 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.5778. Min Act: -0.1700
Data Index: 4233223 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.5778. Min Act: -0.1700
Data Index: 6477222 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.6090. Min Act: -0.1700
Data Index: 6609850 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.5778. Min Act: -0.1700
Data Index: 2130702 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.5153. Min Act: -0.1700
Data Index: 1430759 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.5778. Min Act: -0.1700
Data Index: 3462355 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.5153. Min Act: -0.1700
Data Index: 5553483 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.5153. Min Act: -0.1700
Data Index: 8210102 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.5153. Min Act: -0.1700
Data Index: 8321262 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.5153. Min Act: -0.1700
Data Index: 6459266 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.5153. Min Act: -0.1700
Data Index: 5833592 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7965. Min Range: -4.7965
Max Act: 4.4840. Min Act: -0.1700
Data Index: 3433892 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19