Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 156 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4854. Min Range: -8.4854
Max Act: 8.4854. Min Act: -0.1700
Data Index: 1197384 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4854. Min Range: -8.4854
Max Act: 8.2354. Min Act: -0.1700
Data Index: 1512296 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4854. Min Range: -8.4854
Max Act: 8.2354. Min Act: -0.1700
Data Index: 7587193 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.8604. Min Act: -0.1700
Data Index: 620008 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.7354. Min Act: -0.1700
Data Index: 2900611 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.7666. Min Act: -0.1700
Data Index: 704549 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.7666. Min Act: -0.1700
Data Index: 4082304 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.7041. Min Act: -0.1700
Data Index: 108711 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.6416. Min Act: -0.1700
Data Index: 4463166 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.6416. Min Act: -0.1700
Data Index: 2539832 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.6416. Min Act: -0.1700
Data Index: 2588309 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.6104. Min Act: -0.1700
Data Index: 8326903 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.5791. Min Act: -0.1700
Data Index: 2213074 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.5791. Min Act: -0.1700
Data Index: 8089312 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.5166. Min Act: -0.1700
Data Index: 5782930 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.5166. Min Act: -0.1700
Data Index: 7027264 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.5166. Min Act: -0.1700
Data Index: 3061364 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.5166. Min Act: -0.1700
Data Index: 1223681 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.5166. Min Act: -0.1700
Data Index: 1555686 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4854. Min Range: -8.4854
Max Act: 7.5166. Min Act: -0.1700
Data Index: 6827623 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19