Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2644 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.4142. Min Act: -0.1700
Data Index: 787076 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.1330. Min Act: -0.1700
Data Index: 8680587 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.0705. Min Act: -0.1700
Data Index: 7518788 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.0080. Min Act: -0.1700
Data Index: 4861130 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.9142. Min Act: -0.1700
Data Index: 7866501 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.9142. Min Act: -0.1700
Data Index: 66907 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.8830. Min Act: -0.1700
Data Index: 1918681 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.8205. Min Act: -0.1700
Data Index: 1158401 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.8205. Min Act: -0.1700
Data Index: 8180945 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.8205. Min Act: -0.1700
Data Index: 8290412 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.7892. Min Act: -0.1700
Data Index: 1873142 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.7580. Min Act: -0.1700
Data Index: 6449387 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.7580. Min Act: -0.1700
Data Index: 6008294 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.7580. Min Act: -0.1700
Data Index: 3542671 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.7267. Min Act: -0.1700
Data Index: 6919682 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.7267. Min Act: -0.1700
Data Index: 1160452 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.7267. Min Act: -0.1700
Data Index: 5605930 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.7267. Min Act: -0.1700
Data Index: 583971 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.7267. Min Act: -0.1700
Data Index: 7976440 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4142. Min Range: -6.4142
Max Act: 5.6955. Min Act: -0.1700
Data Index: 2546806 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19