Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.8058. Min Act: -0.1700
Data Index: 4093633 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.6183. Min Act: -0.1700
Data Index: 6323688 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.6808. Min Act: -0.1700
Data Index: 5068137 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.5870. Min Act: -0.1700
Data Index: 3325561 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.5558. Min Act: -0.1700
Data Index: 4964271 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.4933. Min Act: -0.1700
Data Index: 3932552 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.4620. Min Act: -0.1700
Data Index: 2784660 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.4620. Min Act: -0.1699
Data Index: 3088355 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.3370. Min Act: -0.1700
Data Index: 6866171 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.3058. Min Act: -0.1700
Data Index: 1349421 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.2745. Min Act: -0.1700
Data Index: 6252183 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.2745. Min Act: -0.1700
Data Index: 6258691 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.2433. Min Act: -0.1700
Data Index: 7543315 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.1808. Min Act: -0.1700
Data Index: 8546784 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.1495. Min Act: -0.1700
Data Index: 3414678 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.1495. Min Act: -0.1700
Data Index: 8535639 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.1183. Min Act: -0.1700
Data Index: 8381687 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.1183. Min Act: -0.1700
Data Index: 370463 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.1183. Min Act: -0.1700
Data Index: 7624550 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8058. Min Range: -7.8058
Max Act: 7.0870. Min Act: -0.1700
Data Index: 389395 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19