Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.5030. Min Act: -0.1700
Data Index: 863009 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.5030. Min Act: -0.1700
Data Index: 5519546 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.4717. Min Act: -0.1700
Data Index: 49806 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.4717. Min Act: -0.1700
Data Index: 5977108 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.4405. Min Act: -0.1700
Data Index: 5347221 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.4405. Min Act: -0.1700
Data Index: 6314056 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.4717. Min Act: -0.1700
Data Index: 2517355 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.4405. Min Act: -0.1700
Data Index: 6206942 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.4092. Min Act: -0.1700
Data Index: 1494603 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.4092. Min Act: -0.1700
Data Index: 5504646 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.4092. Min Act: -0.1700
Data Index: 6178879 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.3780. Min Act: -0.1700
Data Index: 3180518 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.3780. Min Act: -0.1700
Data Index: 4166600 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.3780. Min Act: -0.1700
Data Index: 2212259 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.3780. Min Act: -0.1700
Data Index: 4521374 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.3780. Min Act: -0.1700
Data Index: 1138834 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.3780. Min Act: -0.1700
Data Index: 3778884 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.3780. Min Act: -0.1700
Data Index: 5201862 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.3467. Min Act: -0.1700
Data Index: 5767477 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5030. Min Range: -4.5030
Max Act: 4.3467. Min Act: -0.1700
Data Index: 1738012 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19