Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3371 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4580. Min Range: -5.4580
Max Act: 5.4580. Min Act: -0.1700
Data Index: 5297090 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4580. Min Range: -5.4580
Max Act: 5.3018. Min Act: -0.1700
Data Index: 7717336 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4580. Min Range: -5.4580
Max Act: 5.2393. Min Act: -0.1700
Data Index: 4903588 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4580. Min Range: -5.4580
Max Act: 5.2080. Min Act: -0.1700
Data Index: 5388010 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4580. Min Range: -5.4580
Max Act: 5.1143. Min Act: -0.1700
Data Index: 7717343 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4580. Min Range: -5.4580
Max Act: 5.0830. Min Act: -0.1700
Data Index: 59664 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4580. Min Range: -5.4580
Max Act: 5.0518. Min Act: -0.1700
Data Index: 1628076 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4580. Min Range: -5.4580
Max Act: 4.9893. Min Act: -0.1700
Data Index: 5631548 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4580. Min Range: -5.4580
Max Act: 5.0205. Min Act: -0.1700
Data Index: 1342442 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4580. Min Range: -5.4580
Max Act: 5.0205. Min Act: -0.1700
Data Index: 707150 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4580. Min Range: -5.4580
Max Act: 4.9893. Min Act: -0.1700
Data Index: 8551130 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4580. Min Range: -5.4580
Max Act: 4.9580. Min Act: -0.1700
Data Index: 2319183 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4580. Min Range: -5.4580
Max Act: 4.9268. Min Act: -0.1700
Data Index: 7717318 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4580. Min Range: -5.4580
Max Act: 4.9580. Min Act: -0.1700
Data Index: 2966902 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4580. Min Range: -5.4580
Max Act: 4.9580. Min Act: -0.1700
Data Index: 8228887 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4580. Min Range: -5.4580
Max Act: 4.9268. Min Act: -0.1700
Data Index: 8259004 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4580. Min Range: -5.4580
Max Act: 4.8955. Min Act: -0.1700
Data Index: 6430183 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4580. Min Range: -5.4580
Max Act: 4.8955. Min Act: -0.1700
Data Index: 2810726 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4580. Min Range: -5.4580
Max Act: 4.8643. Min Act: -0.1700
Data Index: 3572004 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4580. Min Range: -5.4580
Max Act: 4.8643. Min Act: -0.1700
Data Index: 7717327 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19