Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3634 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7435. Min Range: -5.7435
Max Act: 5.7435. Min Act: -0.1700
Data Index: 5378431 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7435. Min Range: -5.7435
Max Act: 5.5873. Min Act: -0.1700
Data Index: 1835919 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7435. Min Range: -5.7435
Max Act: 5.4310. Min Act: -0.1700
Data Index: 6915735 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7435. Min Range: -5.7435
Max Act: 5.3998. Min Act: -0.1700
Data Index: 740773 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7435. Min Range: -5.7435
Max Act: 5.2435. Min Act: -0.1700
Data Index: 7844991 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7435. Min Range: -5.7435
Max Act: 5.1185. Min Act: -0.1700
Data Index: 7087399 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7435. Min Range: -5.7435
Max Act: 5.0873. Min Act: -0.1700
Data Index: 1993129 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7435. Min Range: -5.7435
Max Act: 5.0873. Min Act: -0.1700
Data Index: 1162423 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7435. Min Range: -5.7435
Max Act: 5.0873. Min Act: -0.1700
Data Index: 2053688 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7435. Min Range: -5.7435
Max Act: 5.0873. Min Act: -0.1700
Data Index: 7542517 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7435. Min Range: -5.7435
Max Act: 5.0248. Min Act: -0.1700
Data Index: 6159546 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7435. Min Range: -5.7435
Max Act: 4.9935. Min Act: -0.1700
Data Index: 7265240 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7435. Min Range: -5.7435
Max Act: 5.0248. Min Act: -0.1700
Data Index: 1103479 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7435. Min Range: -5.7435
Max Act: 4.9935. Min Act: -0.1700
Data Index: 2757730 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7435. Min Range: -5.7435
Max Act: 4.9623. Min Act: -0.1700
Data Index: 161386 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7435. Min Range: -5.7435
Max Act: 4.9935. Min Act: -0.1700
Data Index: 510716 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7435. Min Range: -5.7435
Max Act: 4.9935. Min Act: -0.1700
Data Index: 922821 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7435. Min Range: -5.7435
Max Act: 4.9935. Min Act: -0.1700
Data Index: 3076421 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7435. Min Range: -5.7435
Max Act: 4.9935. Min Act: -0.1700
Data Index: 1862783 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7435. Min Range: -5.7435
Max Act: 4.9935. Min Act: -0.1700
Data Index: 6166493 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19