Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4035 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.7249. Min Act: -0.1700
Data Index: 5554955 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.5841. Min Act: -0.1700
Data Index: 7042673 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.5372. Min Act: -0.1700
Data Index: 2453873 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.5215. Min Act: -0.1700
Data Index: 1320852 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.5528. Min Act: -0.1700
Data Index: 6008677 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.5058. Min Act: -0.1700
Data Index: 6186090 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.5058. Min Act: -0.1700
Data Index: 3436650 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.4902. Min Act: -0.1700
Data Index: 4778484 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.4745. Min Act: -0.1700
Data Index: 2299142 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.5058. Min Act: -0.1700
Data Index: 2098194 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.4902. Min Act: -0.1700
Data Index: 5546420 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.4902. Min Act: -0.1700
Data Index: 5805894 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.4745. Min Act: -0.1700
Data Index: 8817927 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.4432. Min Act: -0.1700
Data Index: 6838581 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.4432. Min Act: -0.1700
Data Index: 5372489 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.4118. Min Act: -0.1700
Data Index: 3034826 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.4275. Min Act: -0.1700
Data Index: 2300720 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.4275. Min Act: -0.1700
Data Index: 6634813 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.4118. Min Act: -0.1700
Data Index: 3337700 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7249. Min Range: -3.7249
Max Act: 3.3961. Min Act: -0.1700
Data Index: 6522171 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19