Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4764 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.4908. Min Act: -0.1700
Data Index: 1713262 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.4908. Min Act: -0.1700
Data Index: 6364151 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3968. Min Act: -0.1700
Data Index: 3344428 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3811. Min Act: -0.1700
Data Index: 8088593 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3968. Min Act: -0.1700
Data Index: 5493614 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3968. Min Act: -0.1700
Data Index: 7045974 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3811. Min Act: -0.1700
Data Index: 4855262 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3811. Min Act: -0.1700
Data Index: 7448653 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3341. Min Act: -0.1700
Data Index: 2202711 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3498. Min Act: -0.1700
Data Index: 6908811 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3341. Min Act: -0.1700
Data Index: 852711 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3341. Min Act: -0.1700
Data Index: 6238873 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3184. Min Act: -0.1700
Data Index: 6239278 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3184. Min Act: -0.1700
Data Index: 7586211 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3184. Min Act: -0.1700
Data Index: 7401498 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3184. Min Act: -0.1700
Data Index: 258877 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3184. Min Act: -0.1700
Data Index: 7777979 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.2870. Min Act: -0.1700
Data Index: 6957988 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3184. Min Act: -0.1700
Data Index: 3460070 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4908. Min Range: -3.4908
Max Act: 3.3027. Min Act: -0.1700
Data Index: 532735 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19