Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2246 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8952. Min Act: -0.1700
Data Index: 7571262 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8952. Min Act: -0.1700
Data Index: 7186746 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8952. Min Act: -0.1700
Data Index: 5188539 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8327. Min Act: -0.1700
Data Index: 3602582 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8327. Min Act: -0.1700
Data Index: 7341980 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.8327. Min Act: -0.1700
Data Index: 199812 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7702. Min Act: -0.1700
Data Index: 1402197 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7390. Min Act: -0.1700
Data Index: 500500 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7390. Min Act: -0.1700
Data Index: 4818708 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7077. Min Act: -0.1700
Data Index: 1961632 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7077. Min Act: -0.1700
Data Index: 8078457 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.7077. Min Act: -0.1700
Data Index: 6400328 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6452. Min Act: -0.1700
Data Index: 6045004 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6452. Min Act: -0.1700
Data Index: 5450421 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6452. Min Act: -0.1700
Data Index: 8669769 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6452. Min Act: -0.1700
Data Index: 6012089 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6452. Min Act: -0.1700
Data Index: 6709234 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6452. Min Act: -0.1700
Data Index: 8506764 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6452. Min Act: -0.1700
Data Index: 1188293 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8952. Min Range: -4.8952
Max Act: 4.6452. Min Act: -0.1700
Data Index: 914173 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19