Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3797 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.4839. Min Act: -0.1700
Data Index: 2676858 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.3902. Min Act: -0.1700
Data Index: 3628353 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.2964. Min Act: -0.1700
Data Index: 2676860 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.2339. Min Act: -0.1700
Data Index: 98227 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.2027. Min Act: -0.1700
Data Index: 8459811 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.1402. Min Act: -0.1700
Data Index: 1134315 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.1089. Min Act: -0.1700
Data Index: 882498 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.0777. Min Act: -0.1700
Data Index: 7959714 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.0777. Min Act: -0.1700
Data Index: 3575067 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.0464. Min Act: -0.1700
Data Index: 2938232 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.0777. Min Act: -0.1700
Data Index: 3575071 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.0152. Min Act: -0.1700
Data Index: 6016965 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.0152. Min Act: -0.1700
Data Index: 4185209 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.0152. Min Act: -0.1700
Data Index: 7430001 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.0152. Min Act: -0.1700
Data Index: 5755400 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.0152. Min Act: -0.1700
Data Index: 5755395 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4839. Min Range: -5.4839
Max Act: 5.0152. Min Act: -0.1700
Data Index: 5755401 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4839. Min Range: -5.4839
Max Act: 4.9839. Min Act: -0.1700
Data Index: 5182829 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4839. Min Range: -5.4839
Max Act: 4.9839. Min Act: -0.1700
Data Index: 5755398 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4839. Min Range: -5.4839
Max Act: 4.9839. Min Act: -0.1700
Data Index: 7172196 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19