Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 253 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1128. Min Range: -4.1128
Max Act: 4.1128. Min Act: -0.1700
Data Index: 6296236 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1128. Min Range: -4.1128
Max Act: 4.0816. Min Act: -0.1700
Data Index: 8291959 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1128. Min Range: -4.1128
Max Act: 4.0503. Min Act: -0.1700
Data Index: 3450046 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1128. Min Range: -4.1128
Max Act: 4.0503. Min Act: -0.1700
Data Index: 6303444 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.9878. Min Act: -0.1700
Data Index: 5167882 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.9565. Min Act: -0.1700
Data Index: 5475101 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.9565. Min Act: -0.1700
Data Index: 366560 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.9565. Min Act: -0.1700
Data Index: 8140554 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.8940. Min Act: -0.1700
Data Index: 1458606 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.8940. Min Act: -0.1700
Data Index: 311766 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.9253. Min Act: -0.1700
Data Index: 4502514 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.8627. Min Act: -0.1700
Data Index: 4083778 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.9253. Min Act: -0.1700
Data Index: 3521394 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.8940. Min Act: -0.1700
Data Index: 726958 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.8940. Min Act: -0.1700
Data Index: 2007338 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.8940. Min Act: -0.1700
Data Index: 6007037 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.8940. Min Act: -0.1700
Data Index: 1213205 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.8627. Min Act: -0.1700
Data Index: 5990502 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.8627. Min Act: -0.1700
Data Index: 586564 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1128. Min Range: -4.1128
Max Act: 3.8315. Min Act: -0.1700
Data Index: 4374765 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19