Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5486 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.9783. Min Act: -0.1700
Data Index: 6673739 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.8533. Min Act: -0.1700
Data Index: 147176 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.7908. Min Act: -0.1700
Data Index: 5247426 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.7595. Min Act: -0.1700
Data Index: 2565071 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.7283. Min Act: -0.1700
Data Index: 4340586 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.6970. Min Act: -0.1700
Data Index: 4777846 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.6658. Min Act: -0.1700
Data Index: 3363953 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.6658. Min Act: -0.1700
Data Index: 1690775 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.6658. Min Act: -0.1700
Data Index: 4079599 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.6033. Min Act: -0.1700
Data Index: 1670688 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.6033. Min Act: -0.1700
Data Index: 1118034 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.6345. Min Act: -0.1700
Data Index: 1005597 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.6033. Min Act: -0.1700
Data Index: 2851259 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.6345. Min Act: -0.1700
Data Index: 6312906 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.6345. Min Act: -0.1700
Data Index: 6025765 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.6345. Min Act: -0.1700
Data Index: 7443773 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.6033. Min Act: -0.1700
Data Index: 1185501 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.5720. Min Act: -0.1700
Data Index: 3756058 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.5720. Min Act: -0.1700
Data Index: 4226711 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9783. Min Range: -5.9783
Max Act: 5.5408. Min Act: -0.1700
Data Index: 2383881 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19