Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2322 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.6179. Min Act: -0.1700
Data Index: 3775487 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.5866. Min Act: -0.1700
Data Index: 461437 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.6179. Min Act: -0.1700
Data Index: 4536130 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.5554. Min Act: -0.1700
Data Index: 4555277 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.5241. Min Act: -0.1700
Data Index: 3085123 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.5554. Min Act: -0.1700
Data Index: 1468177 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.5554. Min Act: -0.1700
Data Index: 4238205 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.5241. Min Act: -0.1700
Data Index: 7296988 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.4929. Min Act: -0.1700
Data Index: 6191053 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.4929. Min Act: -0.1700
Data Index: 5008973 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.4929. Min Act: -0.1700
Data Index: 4558567 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.4304. Min Act: -0.1700
Data Index: 4286929 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.4929. Min Act: -0.1700
Data Index: 6250898 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.4929. Min Act: -0.1700
Data Index: 3023817 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.4616. Min Act: -0.1700
Data Index: 3884301 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.4616. Min Act: -0.1700
Data Index: 7571053 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.4304. Min Act: -0.1700
Data Index: 4674808 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.4304. Min Act: -0.1700
Data Index: 916934 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.4304. Min Act: -0.1700
Data Index: 1801487 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6179. Min Range: -4.6179
Max Act: 4.4304. Min Act: -0.1700
Data Index: 951997 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19