Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1564 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.5840. Min Act: -0.1700
Data Index: 6876245 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.5684. Min Act: -0.1700
Data Index: 955405 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.5684. Min Act: -0.1700
Data Index: 2759535 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.5058. Min Act: -0.1700
Data Index: 1981291 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.4117. Min Act: -0.1700
Data Index: 7671420 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.4274. Min Act: -0.1700
Data Index: 2781561 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.3961. Min Act: -0.1700
Data Index: 7760997 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.3961. Min Act: -0.1700
Data Index: 1764922 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.3804. Min Act: -0.1700
Data Index: 2859519 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.3804. Min Act: -0.1700
Data Index: 4345825 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.3804. Min Act: -0.1700
Data Index: 8487398 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.3804. Min Act: -0.1700
Data Index: 3252177 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.3490. Min Act: -0.1700
Data Index: 2124396 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.3490. Min Act: -0.1700
Data Index: 1837183 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.3176. Min Act: -0.1700
Data Index: 8407042 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.3019. Min Act: -0.1700
Data Index: 6302167 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.3019. Min Act: -0.1700
Data Index: 2968305 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.2862. Min Act: -0.1700
Data Index: 1289126 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.3176. Min Act: -0.1700
Data Index: 1264577 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5840. Min Range: -3.5840
Max Act: 3.2705. Min Act: -0.1700
Data Index: 2839577 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19