Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5642 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.4016. Min Act: -0.1700
Data Index: 6083833 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.3704. Min Act: -0.1700
Data Index: 2852192 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.3391. Min Act: -0.1700
Data Index: 457038 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.3079. Min Act: -0.1700
Data Index: 665095 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.2766. Min Act: -0.1700
Data Index: 2972090 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.2454. Min Act: -0.1700
Data Index: 3019221 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.2454. Min Act: -0.1700
Data Index: 219485 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.2454. Min Act: -0.1700
Data Index: 7199244 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.2454. Min Act: -0.1700
Data Index: 6624812 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.2141. Min Act: -0.1700
Data Index: 1177714 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1829. Min Act: -0.1700
Data Index: 2777591 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1516. Min Act: -0.1700
Data Index: 7875532 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1516. Min Act: -0.1700
Data Index: 3873327 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1516. Min Act: -0.1700
Data Index: 4182664 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1516. Min Act: -0.1700
Data Index: 5362138 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1204. Min Act: -0.1700
Data Index: 330412 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1516. Min Act: -0.1700
Data Index: 5467301 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1204. Min Act: -0.1700
Data Index: 4305234 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.0891. Min Act: -0.1700
Data Index: 2492374 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.0891. Min Act: -0.1700
Data Index: 5123480 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19