Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2838 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.7609. Min Act: -0.1700
Data Index: 277805 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.7609. Min Act: -0.1700
Data Index: 5213974 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.7449. Min Act: -0.1700
Data Index: 3066791 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6810. Min Act: -0.1700
Data Index: 379464 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6970. Min Act: -0.1700
Data Index: 3206351 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.7130. Min Act: -0.1700
Data Index: 5819735 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6970. Min Act: -0.1700
Data Index: 2157307 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6970. Min Act: -0.1700
Data Index: 1790858 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6970. Min Act: -0.1700
Data Index: 794978 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6970. Min Act: -0.1700
Data Index: 2168172 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6970. Min Act: -0.1700
Data Index: 2234782 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6810. Min Act: -0.1700
Data Index: 970837 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6810. Min Act: -0.1700
Data Index: 5132762 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6650. Min Act: -0.1700
Data Index: 1816744 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6810. Min Act: -0.1700
Data Index: 987392 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6650. Min Act: -0.1700
Data Index: 5385204 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6489. Min Act: -0.1700
Data Index: 1958132 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6810. Min Act: -0.1700
Data Index: 6489915 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6650. Min Act: -0.1700
Data Index: 6574881 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7609. Min Range: -2.7609
Max Act: 2.6650. Min Act: -0.1700
Data Index: 950194 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19