Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2071 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5892. Min Range: -7.5892
Max Act: 7.5892. Min Act: -0.1700
Data Index: 3085948 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5892. Min Range: -7.5892
Max Act: 7.3080. Min Act: -0.1700
Data Index: 6087874 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.8392. Min Act: -0.1700
Data Index: 47510 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.8705. Min Act: -0.1700
Data Index: 7305897 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.7767. Min Act: -0.1700
Data Index: 5380568 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.7142. Min Act: -0.1700
Data Index: 8561117 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.6830. Min Act: -0.1700
Data Index: 7857913 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.6205. Min Act: -0.1700
Data Index: 2747653 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.6830. Min Act: -0.1700
Data Index: 2757333 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.6830. Min Act: -0.1700
Data Index: 923120 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.6205. Min Act: -0.1700
Data Index: 6232271 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.5892. Min Act: -0.1700
Data Index: 4170168 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.5267. Min Act: -0.1700
Data Index: 367481 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.4955. Min Act: -0.1700
Data Index: 5150830 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.5267. Min Act: -0.1700
Data Index: 374297 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.5267. Min Act: -0.1700
Data Index: 6569342 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.4955. Min Act: -0.1700
Data Index: 428292 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.5267. Min Act: -0.1700
Data Index: 8601855 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.4955. Min Act: -0.1700
Data Index: 4124357 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5892. Min Range: -7.5892
Max Act: 6.4955. Min Act: -0.1700
Data Index: 403170 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19