Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4119. Min Range: -7.4119
Max Act: 7.4119. Min Act: -0.1700
Data Index: 3486501 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4119. Min Range: -7.4119
Max Act: 7.3182. Min Act: -0.1700
Data Index: 8489980 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4119. Min Range: -7.4119
Max Act: 7.2244. Min Act: -0.1700
Data Index: 3685308 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4119. Min Range: -7.4119
Max Act: 7.1307. Min Act: -0.1700
Data Index: 1537235 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4119. Min Range: -7.4119
Max Act: 7.0994. Min Act: -0.1700
Data Index: 6570558 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4119. Min Range: -7.4119
Max Act: 7.0682. Min Act: -0.1700
Data Index: 6842379 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4119. Min Range: -7.4119
Max Act: 7.0369. Min Act: -0.1700
Data Index: 6526816 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4119. Min Range: -7.4119
Max Act: 7.0057. Min Act: -0.1700
Data Index: 1380583 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.9744. Min Act: -0.1700
Data Index: 7618489 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.9432. Min Act: -0.1700
Data Index: 4308697 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.9119. Min Act: -0.1700
Data Index: 171568 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.9119. Min Act: -0.1700
Data Index: 666331 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.8807. Min Act: -0.1700
Data Index: 5174725 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.8807. Min Act: -0.1700
Data Index: 8280748 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.8494. Min Act: -0.1700
Data Index: 5205444 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.8182. Min Act: -0.1700
Data Index: 6472070 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.8182. Min Act: -0.1700
Data Index: 1724667 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.7869. Min Act: -0.1700
Data Index: 2356506 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.7244. Min Act: -0.1700
Data Index: 417327 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4119. Min Range: -7.4119
Max Act: 6.7244. Min Act: -0.1700
Data Index: 3366069 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19