Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.4318. Min Act: -0.1700
Data Index: 5347097 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.3380. Min Act: -0.1700
Data Index: 7214664 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.3068. Min Act: -0.1700
Data Index: 3513965 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.2130. Min Act: -0.1700
Data Index: 587284 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.2130. Min Act: -0.1700
Data Index: 1409921 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.1505. Min Act: -0.1700
Data Index: 886238 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.1505. Min Act: -0.1700
Data Index: 5585165 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.1193. Min Act: -0.1700
Data Index: 5170216 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.0568. Min Act: -0.1700
Data Index: 3446610 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.0880. Min Act: -0.1700
Data Index: 46134 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.1193. Min Act: -0.1700
Data Index: 6672536 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.0880. Min Act: -0.1700
Data Index: 3630098 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.0568. Min Act: -0.1700
Data Index: 5141520 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.0568. Min Act: -0.1700
Data Index: 4995051 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.0568. Min Act: -0.1700
Data Index: 6574802 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.0880. Min Act: -0.1700
Data Index: 6209881 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.0880. Min Act: -0.1700
Data Index: 4641757 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.0568. Min Act: -0.1700
Data Index: 5573400 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.0568. Min Act: -0.1700
Data Index: 240674 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4318. Min Range: -7.4318
Max Act: 7.0568. Min Act: -0.1700
Data Index: 6567945 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19