Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4562 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2870. Min Range: -4.2870
Max Act: 4.2870. Min Act: -0.1700
Data Index: 8606884 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2870. Min Range: -4.2870
Max Act: 4.2245. Min Act: -0.1700
Data Index: 3572486 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2870. Min Range: -4.2870
Max Act: 4.1933. Min Act: -0.1700
Data Index: 3294433 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2870. Min Range: -4.2870
Max Act: 4.1307. Min Act: -0.1700
Data Index: 4533382 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2870. Min Range: -4.2870
Max Act: 4.1307. Min Act: -0.1700
Data Index: 2587926 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2870. Min Range: -4.2870
Max Act: 4.0995. Min Act: -0.1700
Data Index: 485915 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2870. Min Range: -4.2870
Max Act: 4.0682. Min Act: -0.1700
Data Index: 3673471 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2870. Min Range: -4.2870
Max Act: 4.0682. Min Act: -0.1700
Data Index: 3329073 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2870. Min Range: -4.2870
Max Act: 4.0682. Min Act: -0.1700
Data Index: 3138483 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2870. Min Range: -4.2870
Max Act: 4.0057. Min Act: -0.1700
Data Index: 6597467 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2870. Min Range: -4.2870
Max Act: 4.0370. Min Act: -0.1700
Data Index: 7625409 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2870. Min Range: -4.2870
Max Act: 4.0057. Min Act: -0.1700
Data Index: 5903478 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2870. Min Range: -4.2870
Max Act: 4.0057. Min Act: -0.1700
Data Index: 623512 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2870. Min Range: -4.2870
Max Act: 4.0057. Min Act: -0.1700
Data Index: 2860670 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2870. Min Range: -4.2870
Max Act: 3.9745. Min Act: -0.1700
Data Index: 2288357 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2870. Min Range: -4.2870
Max Act: 3.9745. Min Act: -0.1700
Data Index: 2495700 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2870. Min Range: -4.2870
Max Act: 3.9745. Min Act: -0.1700
Data Index: 6015982 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2870. Min Range: -4.2870
Max Act: 4.0057. Min Act: -0.1700
Data Index: 5702357 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2870. Min Range: -4.2870
Max Act: 3.9432. Min Act: -0.1700
Data Index: 7361623 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2870. Min Range: -4.2870
Max Act: 3.9432. Min Act: -0.1700
Data Index: 175279 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19