Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2923 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.5492. Min Act: -0.1700
Data Index: 4129286 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.4242. Min Act: -0.1700
Data Index: 1988957 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.4554. Min Act: -0.1700
Data Index: 1367813 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.3929. Min Act: -0.1700
Data Index: 2240025 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.4242. Min Act: -0.1700
Data Index: 2242366 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.2992. Min Act: -0.1700
Data Index: 221273 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.2992. Min Act: -0.1700
Data Index: 3008604 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.2679. Min Act: -0.1700
Data Index: 7912509 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.2992. Min Act: -0.1700
Data Index: 6838280 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.2679. Min Act: -0.1700
Data Index: 3421666 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.2367. Min Act: -0.1700
Data Index: 7924342 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.2367. Min Act: -0.1700
Data Index: 2434565 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.2054. Min Act: -0.1700
Data Index: 3886040 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.1429. Min Act: -0.1700
Data Index: 3073149 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.1429. Min Act: -0.1700
Data Index: 4018535 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.1117. Min Act: -0.1700
Data Index: 2340220 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.0804. Min Act: -0.1700
Data Index: 6670104 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.0804. Min Act: -0.1700
Data Index: 4491298 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.0804. Min Act: -0.1700
Data Index: 6850584 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5492. Min Range: -6.5492
Max Act: 6.0804. Min Act: -0.1700
Data Index: 4965421 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19