Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4206 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4257. Min Range: -8.4257
Max Act: 8.4257. Min Act: -0.1700
Data Index: 7183042 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4257. Min Range: -8.4257
Max Act: 8.3007. Min Act: -0.1700
Data Index: 1994167 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4257. Min Range: -8.4257
Max Act: 8.1757. Min Act: -0.1700
Data Index: 7306907 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4257. Min Range: -8.4257
Max Act: 8.1132. Min Act: -0.1700
Data Index: 8297871 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.9257. Min Act: -0.1700
Data Index: 4046552 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.8632. Min Act: -0.1700
Data Index: 6555913 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.8632. Min Act: -0.1700
Data Index: 4981136 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.8007. Min Act: -0.1700
Data Index: 8460981 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.8632. Min Act: -0.1700
Data Index: 2365342 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.8632. Min Act: -0.1700
Data Index: 936169 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.8632. Min Act: -0.1700
Data Index: 4435707 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.8632. Min Act: -0.1700
Data Index: 942145 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.8007. Min Act: -0.1698
Data Index: 8218926 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.8007. Min Act: -0.1700
Data Index: 298039 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.8007. Min Act: -0.1700
Data Index: 4866452 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.8007. Min Act: -0.1700
Data Index: 7645578 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.8007. Min Act: -0.1700
Data Index: 7833092 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.7382. Min Act: -0.1700
Data Index: 5656160 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.8007. Min Act: -0.1700
Data Index: 8588713 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4257. Min Range: -8.4257
Max Act: 7.7382. Min Act: -0.1700
Data Index: 1597451 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19