Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2100 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.9524. Min Act: -0.1700
Data Index: 4849778 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.9211. Min Act: -0.1700
Data Index: 783211 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.7024. Min Act: -0.1700
Data Index: 1041540 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.6399. Min Act: -0.1700
Data Index: 2066650 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.6399. Min Act: -0.1700
Data Index: 783212 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.6399. Min Act: -0.1700
Data Index: 2126307 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.5774. Min Act: -0.1700
Data Index: 701870 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.5461. Min Act: -0.1700
Data Index: 2549719 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.5461. Min Act: -0.1700
Data Index: 6402815 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.5149. Min Act: -0.1700
Data Index: 7059784 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.5149. Min Act: -0.1700
Data Index: 2206709 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.4836. Min Act: -0.1700
Data Index: 1649909 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.4836. Min Act: -0.1700
Data Index: 5243951 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.4836. Min Act: -0.1700
Data Index: 5989111 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.4836. Min Act: -0.1700
Data Index: 8616654 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.4836. Min Act: -0.1700
Data Index: 2928374 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.4524. Min Act: -0.1700
Data Index: 5115682 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.4524. Min Act: -0.1700
Data Index: 8709269 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.4836. Min Act: -0.1700
Data Index: 2948151 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9524. Min Range: -6.9524
Max Act: 6.4211. Min Act: -0.1700
Data Index: 1301336 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19