Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3189 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2580. Min Range: -6.2580
Max Act: 6.2580. Min Act: -0.1700
Data Index: 8057735 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2580. Min Range: -6.2580
Max Act: 6.1330. Min Act: -0.1700
Data Index: 7459451 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2580. Min Range: -6.2580
Max Act: 6.1018. Min Act: -0.1700
Data Index: 5710168 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2580. Min Range: -6.2580
Max Act: 6.0705. Min Act: -0.1700
Data Index: 5876024 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.9768. Min Act: -0.1700
Data Index: 5760029 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.9768. Min Act: -0.1700
Data Index: 8057731 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.9455. Min Act: -0.1700
Data Index: 4377440 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.9455. Min Act: -0.1700
Data Index: 8057736 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.9768. Min Act: -0.1700
Data Index: 872637 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.9455. Min Act: -0.1700
Data Index: 6069435 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.8830. Min Act: -0.1700
Data Index: 1283861 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.7893. Min Act: -0.1700
Data Index: 3593301 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.8205. Min Act: -0.1700
Data Index: 338968 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.8205. Min Act: -0.1700
Data Index: 738204 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.8205. Min Act: -0.1700
Data Index: 929785 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.8205. Min Act: -0.1700
Data Index: 7417400 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.7580. Min Act: -0.1700
Data Index: 7688074 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.7268. Min Act: -0.1700
Data Index: 3650069 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.7580. Min Act: -0.1700
Data Index: 3651744 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2580. Min Range: -6.2580
Max Act: 5.7268. Min Act: -0.1700
Data Index: 7563841 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19