Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 648 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.4190. Min Act: -0.1700
Data Index: 8258570 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.3565. Min Act: -0.1700
Data Index: 4972976 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.3253. Min Act: -0.1700
Data Index: 8185890 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.2940. Min Act: -0.1700
Data Index: 3746047 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.2315. Min Act: -0.1700
Data Index: 1445326 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1690. Min Act: -0.1700
Data Index: 3673408 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1690. Min Act: -0.1700
Data Index: 876766 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1690. Min Act: -0.1700
Data Index: 2514308 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1690. Min Act: -0.1700
Data Index: 7726246 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1378. Min Act: -0.1700
Data Index: 8017730 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1065. Min Act: -0.1700
Data Index: 2598617 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1065. Min Act: -0.1700
Data Index: 3385862 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1378. Min Act: -0.1700
Data Index: 7072889 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1065. Min Act: -0.1700
Data Index: 4114944 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1065. Min Act: -0.1700
Data Index: 8065770 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1378. Min Act: -0.1700
Data Index: 28247 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1378. Min Act: -0.1700
Data Index: 3871189 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.0753. Min Act: -0.1700
Data Index: 391368 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.0440. Min Act: -0.1700
Data Index: 4888144 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1065. Min Act: -0.1700
Data Index: 4111516 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19