Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3374 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.3230. Min Act: -0.1700
Data Index: 6806796 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.2605. Min Act: -0.1700
Data Index: 5013977 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.1668. Min Act: -0.1700
Data Index: 2552071 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.1980. Min Act: -0.1700
Data Index: 325654 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.2293. Min Act: -0.1700
Data Index: 1788267 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.1980. Min Act: -0.1700
Data Index: 4119678 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.1980. Min Act: -0.1700
Data Index: 5512417 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.1668. Min Act: -0.1700
Data Index: 2649081 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.1668. Min Act: -0.1700
Data Index: 7781296 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.1043. Min Act: -0.1700
Data Index: 3717704 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.1043. Min Act: -0.1700
Data Index: 3798907 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.1043. Min Act: -0.1700
Data Index: 1547554 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.1043. Min Act: -0.1700
Data Index: 6623080 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.0730. Min Act: -0.1700
Data Index: 3868703 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.0730. Min Act: -0.1700
Data Index: 192189 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.0730. Min Act: -0.1700
Data Index: 5359741 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.0418. Min Act: -0.1700
Data Index: 4170998 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.0105. Min Act: -0.1700
Data Index: 919408 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.0418. Min Act: -0.1700
Data Index: 8641696 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3230. Min Range: -5.3230
Max Act: 5.0418. Min Act: -0.1700
Data Index: 5853660 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19