Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5046 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.8735. Min Act: -0.1700
Data Index: 7182214 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.3423. Min Act: -0.1700
Data Index: 2969764 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.3110. Min Act: -0.1700
Data Index: 5634344 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.2173. Min Act: -0.1700
Data Index: 7189394 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.1235. Min Act: -0.1700
Data Index: 7249876 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.1235. Min Act: -0.1700
Data Index: 6037040 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.1235. Min Act: -0.1700
Data Index: 6724798 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.0923. Min Act: -0.1700
Data Index: 4284217 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.0923. Min Act: -0.1700
Data Index: 2870340 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.0923. Min Act: -0.1700
Data Index: 764036 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8735. Min Range: -6.8735
Max Act: 6.0610. Min Act: -0.1700
Data Index: 6918654 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8735. Min Range: -6.8735
Max Act: 5.9985. Min Act: -0.1700
Data Index: 4578991 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8735. Min Range: -6.8735
Max Act: 5.9985. Min Act: -0.1700
Data Index: 4387728 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8735. Min Range: -6.8735
Max Act: 5.9985. Min Act: -0.1700
Data Index: 377117 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8735. Min Range: -6.8735
Max Act: 5.9985. Min Act: -0.1700
Data Index: 7007994 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8735. Min Range: -6.8735
Max Act: 5.9985. Min Act: -0.1700
Data Index: 3153415 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8735. Min Range: -6.8735
Max Act: 5.9985. Min Act: -0.1700
Data Index: 1275321 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8735. Min Range: -6.8735
Max Act: 5.9985. Min Act: -0.1700
Data Index: 721741 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8735. Min Range: -6.8735
Max Act: 5.9985. Min Act: -0.1700
Data Index: 1594827 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8735. Min Range: -6.8735
Max Act: 5.9673. Min Act: -0.1700
Data Index: 7613511 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19