Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4650 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.3818. Min Act: -0.1700
Data Index: 4643278 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.3190. Min Act: -0.1700
Data Index: 8136833 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.2091. Min Act: -0.1700
Data Index: 3944285 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.1934. Min Act: -0.1700
Data Index: 8196144 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.1776. Min Act: -0.1700
Data Index: 6403900 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.1304. Min Act: -0.1700
Data Index: 4860996 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.1304. Min Act: -0.1700
Data Index: 8570118 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.1304. Min Act: -0.1700
Data Index: 265693 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.1147. Min Act: -0.1700
Data Index: 8631888 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.1462. Min Act: -0.1700
Data Index: 7070150 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.1304. Min Act: -0.1700
Data Index: 8067124 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.1147. Min Act: -0.1700
Data Index: 5445057 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.0989. Min Act: -0.1700
Data Index: 1450624 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.0831. Min Act: -0.1700
Data Index: 6782191 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.0831. Min Act: -0.1700
Data Index: 2502112 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.0674. Min Act: -0.1700
Data Index: 7670495 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.0516. Min Act: -0.1700
Data Index: 4930548 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.0358. Min Act: -0.1700
Data Index: 7001943 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.0516. Min Act: -0.1700
Data Index: 4103109 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3818. Min Range: -3.3818
Max Act: 3.0358. Min Act: -0.1700
Data Index: 7338625 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19