Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1759 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2864. Min Range: -6.2864
Max Act: 6.2864. Min Act: -0.1700
Data Index: 7818603 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.9739. Min Act: -0.1700
Data Index: 8143955 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.8489. Min Act: -0.1700
Data Index: 2104877 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.8802. Min Act: -0.1700
Data Index: 792070 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.8802. Min Act: -0.1700
Data Index: 7020352 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.8177. Min Act: -0.1700
Data Index: 6717278 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.8177. Min Act: -0.1700
Data Index: 3794197 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.7239. Min Act: -0.1700
Data Index: 990506 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.7239. Min Act: -0.1700
Data Index: 3424509 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.7239. Min Act: -0.1700
Data Index: 3343833 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.7239. Min Act: -0.1700
Data Index: 6380593 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.6927. Min Act: -0.1700
Data Index: 4877433 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.6927. Min Act: -0.1700
Data Index: 683985 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.6927. Min Act: -0.1700
Data Index: 2485774 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.6614. Min Act: -0.1700
Data Index: 5955471 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.6614. Min Act: -0.1700
Data Index: 6567301 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.6302. Min Act: -0.1700
Data Index: 6338673 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.5989. Min Act: -0.1700
Data Index: 357642 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.6614. Min Act: -0.1700
Data Index: 5108852 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2864. Min Range: -6.2864
Max Act: 5.5989. Min Act: -0.1700
Data Index: 2799124 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19