Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3098 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.9498. Min Act: -0.1700
Data Index: 1802812 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.9185. Min Act: -0.1700
Data Index: 541512 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.7623. Min Act: -0.1700
Data Index: 1015140 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.7623. Min Act: -0.1700
Data Index: 6035814 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.6998. Min Act: -0.1700
Data Index: 5475312 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.6685. Min Act: -0.1700
Data Index: 2041034 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.6685. Min Act: -0.1700
Data Index: 7196194 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.6060. Min Act: -0.1700
Data Index: 8570826 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.6060. Min Act: -0.1700
Data Index: 3838053 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.6373. Min Act: -0.1700
Data Index: 2236335 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.5748. Min Act: -0.1700
Data Index: 1447389 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.5435. Min Act: -0.1700
Data Index: 8188274 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.5435. Min Act: -0.1700
Data Index: 3905118 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.5435. Min Act: -0.1700
Data Index: 3717621 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.4810. Min Act: -0.1700
Data Index: 534420 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.5123. Min Act: -0.1700
Data Index: 6866924 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.4810. Min Act: -0.1700
Data Index: 6773478 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.4810. Min Act: -0.1700
Data Index: 6947646 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.5123. Min Act: -0.1700
Data Index: 3269528 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9498. Min Range: -6.9498
Max Act: 6.4810. Min Act: -0.1700
Data Index: 4544252 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19