Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1589 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 8.3489. Min Range: -8.3489
Max Act: 8.3489. Min Act: -0.1700
Data Index: 4955454 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3489. Min Range: -8.3489
Max Act: 8.0989. Min Act: -0.1700
Data Index: 1224063 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3489. Min Range: -8.3489
Max Act: 8.0989. Min Act: -0.1700
Data Index: 4771942 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3489. Min Range: -8.3489
Max Act: 8.0364. Min Act: -0.1700
Data Index: 3573204 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.9739. Min Act: -0.1700
Data Index: 4518096 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.9114. Min Act: -0.1700
Data Index: 3277730 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.9114. Min Act: -0.1700
Data Index: 966806 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.8489. Min Act: -0.1700
Data Index: 6865819 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.8489. Min Act: -0.1700
Data Index: 5776709 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.9114. Min Act: -0.1700
Data Index: 4234135 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.8489. Min Act: -0.1700
Data Index: 4817987 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.9114. Min Act: -0.1700
Data Index: 8779908 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.8489. Min Act: -0.1700
Data Index: 8007699 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.7864. Min Act: -0.1700
Data Index: 7507105 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.8489. Min Act: -0.1700
Data Index: 7340266 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.8489. Min Act: -0.1700
Data Index: 1395916 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.8489. Min Act: -0.1700
Data Index: 37554 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.7864. Min Act: -0.1700
Data Index: 4280985 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.7239. Min Act: -0.1700
Data Index: 2099712 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3489. Min Range: -8.3489
Max Act: 7.7864. Min Act: -0.1700
Data Index: 369782 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19