Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2793 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.9216. Min Act: -0.1700
Data Index: 189868 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.5153. Min Act: -0.1700
Data Index: 2589795 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.4216. Min Act: -0.1700
Data Index: 6148516 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.4216. Min Act: -0.1700
Data Index: 8189857 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.3903. Min Act: -0.1700
Data Index: 2897311 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.3278. Min Act: -0.1700
Data Index: 2483873 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.2966. Min Act: -0.1700
Data Index: 832351 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.2653. Min Act: -0.1700
Data Index: 8548285 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.2653. Min Act: -0.1700
Data Index: 3974110 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.2028. Min Act: -0.1700
Data Index: 4004199 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.2028. Min Act: -0.1700
Data Index: 4430807 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.1091. Min Act: -0.1700
Data Index: 609285 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.1716. Min Act: -0.1700
Data Index: 4435019 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.1403. Min Act: -0.1700
Data Index: 5951927 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.1091. Min Act: -0.1700
Data Index: 8493993 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.0778. Min Act: -0.1700
Data Index: 7918463 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.0778. Min Act: -0.1700
Data Index: 4435021 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.0466. Min Act: -0.1700
Data Index: 5058592 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.0153. Min Act: -0.1700
Data Index: 5942465 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9216. Min Range: -7.9216
Max Act: 7.0153. Min Act: -0.1700
Data Index: 3136329 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19