Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3242. Min Range: -3.3242
Max Act: 3.3242. Min Act: -0.1700
Data Index: 570936 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3242. Min Range: -3.3242
Max Act: 3.1513. Min Act: -0.1700
Data Index: 4530158 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3242. Min Range: -3.3242
Max Act: 3.0568. Min Act: -0.1700
Data Index: 4317869 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3242. Min Range: -3.3242
Max Act: 3.0410. Min Act: -0.1700
Data Index: 6629907 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3242. Min Range: -3.3242
Max Act: 3.1041. Min Act: -0.1700
Data Index: 322132 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3242. Min Range: -3.3242
Max Act: 3.0410. Min Act: -0.1700
Data Index: 6872944 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3242. Min Range: -3.3242
Max Act: 3.0410. Min Act: -0.1700
Data Index: 715647 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3242. Min Range: -3.3242
Max Act: 3.0410. Min Act: -0.1700
Data Index: 1609760 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3242. Min Range: -3.3242
Max Act: 3.0094. Min Act: -0.1700
Data Index: 367912 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3242. Min Range: -3.3242
Max Act: 3.0568. Min Act: -0.1700
Data Index: 354226 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3242. Min Range: -3.3242
Max Act: 2.9303. Min Act: -0.1700
Data Index: 7183819 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3242. Min Range: -3.3242
Max Act: 2.8986. Min Act: -0.1700
Data Index: 4025897 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3242. Min Range: -3.3242
Max Act: 2.9303. Min Act: -0.1700
Data Index: 354235 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3242. Min Range: -3.3242
Max Act: 2.9936. Min Act: -0.1700
Data Index: 4934968 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3242. Min Range: -3.3242
Max Act: 2.9936. Min Act: -0.1700
Data Index: 8215122 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3242. Min Range: -3.3242
Max Act: 2.9778. Min Act: -0.1700
Data Index: 5372779 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3242. Min Range: -3.3242
Max Act: 2.9936. Min Act: -0.1700
Data Index: 825473 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3242. Min Range: -3.3242
Max Act: 3.0094. Min Act: -0.1700
Data Index: 889546 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3242. Min Range: -3.3242
Max Act: 2.9936. Min Act: -0.1700
Data Index: 3984656 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3242. Min Range: -3.3242
Max Act: 2.9145. Min Act: -0.1700
Data Index: 1984327 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19