Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3119 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.7191. Min Act: -0.1700
Data Index: 976608 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.6566. Min Act: -0.1700
Data Index: 2706574 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.5941. Min Act: -0.1700
Data Index: 6297372 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.5316. Min Act: -0.1700
Data Index: 8125459 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.5004. Min Act: -0.1700
Data Index: 3747420 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.4691. Min Act: -0.1700
Data Index: 3030916 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.4066. Min Act: -0.1700
Data Index: 7431476 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.2816. Min Act: -0.1700
Data Index: 1779535 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.2504. Min Act: -0.1700
Data Index: 7612993 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.2504. Min Act: -0.1700
Data Index: 6005622 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.2504. Min Act: -0.1700
Data Index: 6226591 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.1879. Min Act: -0.1700
Data Index: 3226565 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.1566. Min Act: -0.1700
Data Index: 6279818 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.1566. Min Act: -0.1700
Data Index: 7693286 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.1254. Min Act: -0.1700
Data Index: 6073056 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.1254. Min Act: -0.1700
Data Index: 7637166 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.0941. Min Act: -0.1700
Data Index: 4893595 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.0629. Min Act: -0.1700
Data Index: 4477448 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.0629. Min Act: -0.1700
Data Index: 6852715 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7191. Min Range: -6.7191
Max Act: 6.0629. Min Act: -0.1700
Data Index: 7987384 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19