Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5520 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4829. Min Range: -9.4829
Max Act: 9.4204. Min Act: -0.1700
Data Index: 7150753 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4829. Min Range: -9.4829
Max Act: 9.4829. Min Act: -0.1700
Data Index: 1719796 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4829. Min Range: -9.4829
Max Act: 9.2329. Min Act: -0.1700
Data Index: 802161 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4829. Min Range: -9.4829
Max Act: 9.1704. Min Act: -0.1700
Data Index: 8412221 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4829. Min Range: -9.4829
Max Act: 9.0454. Min Act: -0.1700
Data Index: 6073890 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4829. Min Range: -9.4829
Max Act: 8.9829. Min Act: -0.1700
Data Index: 6871317 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4829. Min Range: -9.4829
Max Act: 8.9204. Min Act: -0.1700
Data Index: 8170841 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4829. Min Range: -9.4829
Max Act: 8.9204. Min Act: -0.1700
Data Index: 8139313 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4829. Min Range: -9.4829
Max Act: 8.8579. Min Act: -0.1700
Data Index: 7017715 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4829. Min Range: -9.4829
Max Act: 8.8579. Min Act: -0.1700
Data Index: 8201051 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4829. Min Range: -9.4829
Max Act: 8.8579. Min Act: -0.1700
Data Index: 4542593 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4829. Min Range: -9.4829
Max Act: 8.7954. Min Act: -0.1700
Data Index: 5307791 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4829. Min Range: -9.4829
Max Act: 8.7954. Min Act: -0.1700
Data Index: 1871750 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4829. Min Range: -9.4829
Max Act: 8.7329. Min Act: -0.1700
Data Index: 4950044 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4829. Min Range: -9.4829
Max Act: 8.7329. Min Act: -0.1700
Data Index: 2452530 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4829. Min Range: -9.4829
Max Act: 8.6704. Min Act: -0.1700
Data Index: 5329032 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4829. Min Range: -9.4829
Max Act: 8.6704. Min Act: -0.1700
Data Index: 8002120 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4829. Min Range: -9.4829
Max Act: 8.6704. Min Act: -0.1700
Data Index: 8084757 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4829. Min Range: -9.4829
Max Act: 8.6704. Min Act: -0.1700
Data Index: 1583445 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4829. Min Range: -9.4829
Max Act: 8.6079. Min Act: -0.1700
Data Index: 2488194 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19