Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2924 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1204. Min Range: -10.1204
Max Act: 10.1204. Min Act: -0.1700
Data Index: 5742528 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.8079. Min Act: -0.1700
Data Index: 110517 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.7454. Min Act: -0.1700
Data Index: 5708316 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.6829. Min Act: -0.1700
Data Index: 3750395 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.6829. Min Act: -0.1700
Data Index: 1658079 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.6829. Min Act: -0.1700
Data Index: 317 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.5579. Min Act: -0.1700
Data Index: 7965053 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.4954. Min Act: -0.1700
Data Index: 539471 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.4954. Min Act: -0.1700
Data Index: 7054935 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.3704. Min Act: -0.1700
Data Index: 7838060 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.3704. Min Act: -0.1700
Data Index: 8563168 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.3704. Min Act: -0.1700
Data Index: 6987064 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.3704. Min Act: -0.1700
Data Index: 4675433 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.3704. Min Act: -0.1700
Data Index: 58462 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.3079. Min Act: -0.1700
Data Index: 6560899 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.3079. Min Act: -0.1700
Data Index: 5861029 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.3704. Min Act: -0.1700
Data Index: 2816208 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.3079. Min Act: -0.1700
Data Index: 1206490 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.3079. Min Act: -0.1700
Data Index: 7444512 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1204. Min Range: -10.1204
Max Act: 9.2454. Min Act: -0.1700
Data Index: 614799 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19