Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3295 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.8990. Min Act: -0.1700
Data Index: 6973861 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.6490. Min Act: -0.1700
Data Index: 1966390 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.5240. Min Act: -0.1700
Data Index: 5187061 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.3052. Min Act: -0.1700
Data Index: 7382928 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.3052. Min Act: -0.1700
Data Index: 1730600 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.2427. Min Act: -0.1700
Data Index: 6975952 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.2115. Min Act: -0.1700
Data Index: 830392 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.2115. Min Act: -0.1700
Data Index: 6633135 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.2115. Min Act: -0.1700
Data Index: 4011074 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.1802. Min Act: -0.1700
Data Index: 2590852 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.1802. Min Act: -0.1700
Data Index: 196191 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.1490. Min Act: -0.1700
Data Index: 10478 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.1490. Min Act: -0.1700
Data Index: 1180365 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.1490. Min Act: -0.1700
Data Index: 5465908 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.1177. Min Act: -0.1700
Data Index: 3998393 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.0865. Min Act: -0.1700
Data Index: 8716721 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.0865. Min Act: -0.1700
Data Index: 8262113 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.0865. Min Act: -0.1700
Data Index: 3894860 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.0240. Min Act: -0.1700
Data Index: 1660943 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8990. Min Range: -7.8990
Max Act: 7.0552. Min Act: -0.1700
Data Index: 343875 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19