Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4002 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.9754. Min Act: -0.1700
Data Index: 854688 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.8504. Min Act: -0.1700
Data Index: 6387639 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.7879. Min Act: -0.1700
Data Index: 3844590 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.7254. Min Act: -0.1700
Data Index: 8690848 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.7254. Min Act: -0.1700
Data Index: 8690849 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.6629. Min Act: -0.1700
Data Index: 6502184 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.6629. Min Act: -0.1700
Data Index: 4821930 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.6004. Min Act: -0.1700
Data Index: 4247075 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.6004. Min Act: -0.1700
Data Index: 323609 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.5379. Min Act: -0.1700
Data Index: 5097504 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.5379. Min Act: -0.1700
Data Index: 7560165 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.5379. Min Act: -0.1700
Data Index: 6537420 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.5379. Min Act: -0.1700
Data Index: 7462437 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.5379. Min Act: -0.1700
Data Index: 4500742 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.4129. Min Act: -0.1700
Data Index: 2624545 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.4754. Min Act: -0.1700
Data Index: 7929587 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.4754. Min Act: -0.1700
Data Index: 6743854 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.4754. Min Act: -0.1700
Data Index: 1311637 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.4754. Min Act: -0.1700
Data Index: 7726577 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9754. Min Range: -8.9754
Max Act: 8.4129. Min Act: -0.1700
Data Index: 4124284 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19