Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5784 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.8615. Min Act: -0.1700
Data Index: 3467163 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.7990. Min Act: -0.1700
Data Index: 2671403 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.8302. Min Act: -0.1700
Data Index: 1513891 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.7990. Min Act: -0.1700
Data Index: 5886570 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.7990. Min Act: -0.1700
Data Index: 1997308 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.7990. Min Act: -0.1700
Data Index: 4959048 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.7990. Min Act: -0.1700
Data Index: 646267 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.7990. Min Act: -0.1700
Data Index: 2990664 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.7208. Min Act: -0.1700
Data Index: 5301673 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.7208. Min Act: -0.1700
Data Index: 5908581 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.7051. Min Act: -0.1700
Data Index: 4626480 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.7051. Min Act: -0.1700
Data Index: 2473013 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.7051. Min Act: -0.1700
Data Index: 4952680 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.6895. Min Act: -0.1700
Data Index: 8588490 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.6895. Min Act: -0.1700
Data Index: 6379691 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.6895. Min Act: -0.1700
Data Index: 914522 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.6582. Min Act: -0.1700
Data Index: 1998228 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.6425. Min Act: -0.1700
Data Index: 1162093 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.6738. Min Act: -0.1700
Data Index: 8317647 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8615. Min Range: -3.8615
Max Act: 3.6425. Min Act: -0.1700
Data Index: 7134617 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19