Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2900 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.9895. Min Act: -0.1700
Data Index: 3832183 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.5208. Min Act: -0.1700
Data Index: 780803 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.5208. Min Act: -0.1700
Data Index: 4809768 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.5520. Min Act: -0.1700
Data Index: 4809762 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.4895. Min Act: -0.1700
Data Index: 1661593 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.4270. Min Act: -0.1700
Data Index: 2685485 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.4270. Min Act: -0.1700
Data Index: 7291413 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.4270. Min Act: -0.1700
Data Index: 7862536 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.3958. Min Act: -0.1700
Data Index: 1696459 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.3958. Min Act: -0.1700
Data Index: 4809766 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.3333. Min Act: -0.1700
Data Index: 650906 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.3645. Min Act: -0.1700
Data Index: 3011576 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.3333. Min Act: -0.1700
Data Index: 2447671 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.3333. Min Act: -0.1700
Data Index: 3832185 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.3333. Min Act: -0.1700
Data Index: 2249082 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.3333. Min Act: -0.1700
Data Index: 5838084 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.3020. Min Act: -0.1700
Data Index: 4974952 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.3020. Min Act: -0.1700
Data Index: 8450634 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.3020. Min Act: -0.1700
Data Index: 1867813 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9895. Min Range: -4.9895
Max Act: 4.3020. Min Act: -0.1700
Data Index: 8450655 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19