Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3805 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.1676. Min Act: -0.1700
Data Index: 7204811 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.1676. Min Act: -0.1700
Data Index: 2257432 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.1364. Min Act: -0.1700
Data Index: 7887473 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.1364. Min Act: -0.1700
Data Index: 3388913 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.1364. Min Act: -0.1700
Data Index: 4250914 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.0739. Min Act: -0.1700
Data Index: 5106256 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.0426. Min Act: -0.1700
Data Index: 5307945 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.0739. Min Act: -0.1700
Data Index: 4340190 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.0426. Min Act: -0.1700
Data Index: 242682 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.0426. Min Act: -0.1700
Data Index: 1084360 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.0426. Min Act: -0.1700
Data Index: 5933696 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.0114. Min Act: -0.1700
Data Index: 1147603 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.0114. Min Act: -0.1700
Data Index: 7963548 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.0426. Min Act: -0.1700
Data Index: 8035061 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.0426. Min Act: -0.1700
Data Index: 8736040 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.0114. Min Act: -0.1700
Data Index: 6804131 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1676. Min Range: -5.1676
Max Act: 5.0114. Min Act: -0.1700
Data Index: 5806333 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1676. Min Range: -5.1676
Max Act: 4.9801. Min Act: -0.1700
Data Index: 4789204 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1676. Min Range: -5.1676
Max Act: 4.9801. Min Act: -0.1700
Data Index: 5279785 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1676. Min Range: -5.1676
Max Act: 4.9801. Min Act: -0.1700
Data Index: 1282602 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19