Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4220 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2489. Min Range: -5.2489
Max Act: 5.2489. Min Act: -0.1700
Data Index: 3434105 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2489. Min Range: -5.2489
Max Act: 5.1239. Min Act: -0.1700
Data Index: 7848583 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2489. Min Range: -5.2489
Max Act: 5.0927. Min Act: -0.1700
Data Index: 4113198 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2489. Min Range: -5.2489
Max Act: 5.0302. Min Act: -0.1700
Data Index: 2052487 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.9989. Min Act: -0.1700
Data Index: 5643104 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.9677. Min Act: -0.1700
Data Index: 6756214 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.9364. Min Act: -0.1700
Data Index: 8505824 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.8739. Min Act: -0.1700
Data Index: 3436617 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.8739. Min Act: -0.1700
Data Index: 2340415 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.8739. Min Act: -0.1700
Data Index: 4235193 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.8427. Min Act: -0.1700
Data Index: 567360 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.8427. Min Act: -0.1700
Data Index: 8285117 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.8114. Min Act: -0.1700
Data Index: 2024573 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.7489. Min Act: -0.1700
Data Index: 6948971 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.7489. Min Act: -0.1700
Data Index: 308951 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.7177. Min Act: -0.1700
Data Index: 1331355 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.7177. Min Act: -0.1700
Data Index: 6786820 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.7489. Min Act: -0.1700
Data Index: 5702505 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.6864. Min Act: -0.1700
Data Index: 5115944 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2489. Min Range: -5.2489
Max Act: 4.6864. Min Act: -0.1700
Data Index: 3467022 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19