Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3449 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0127. Min Range: -7.0127
Max Act: 7.0127. Min Act: -0.1700
Data Index: 4674616 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.5127. Min Act: -0.1700
Data Index: 4481098 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.4815. Min Act: -0.1700
Data Index: 2217019 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.4190. Min Act: -0.1700
Data Index: 2239954 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.3252. Min Act: -0.1700
Data Index: 3774107 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.3252. Min Act: -0.1700
Data Index: 6924451 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.2940. Min Act: -0.1700
Data Index: 2100284 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.2315. Min Act: -0.1700
Data Index: 183678 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.2315. Min Act: -0.1700
Data Index: 4411681 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.2315. Min Act: -0.1700
Data Index: 7926483 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.2002. Min Act: -0.1700
Data Index: 7859139 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.2002. Min Act: -0.1700
Data Index: 4130046 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.2002. Min Act: -0.1700
Data Index: 7950243 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.2002. Min Act: -0.1700
Data Index: 3408711 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.2002. Min Act: -0.1700
Data Index: 2210874 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.1690. Min Act: -0.1700
Data Index: 1620383 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.2002. Min Act: -0.1700
Data Index: 7537980 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.1690. Min Act: -0.1700
Data Index: 387006 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.1690. Min Act: -0.1700
Data Index: 2484954 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0127. Min Range: -7.0127
Max Act: 6.1377. Min Act: -0.1700
Data Index: 5239844 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19