Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7109. Min Range: -6.7109
Max Act: 6.7109. Min Act: -0.1700
Data Index: 3706360 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7109. Min Range: -6.7109
Max Act: 6.7109. Min Act: -0.1700
Data Index: 449471 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7109. Min Range: -6.7109
Max Act: 6.3359. Min Act: -0.1700
Data Index: 5676644 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7109. Min Range: -6.7109
Max Act: 6.1171. Min Act: -0.1700
Data Index: 8214044 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7109. Min Range: -6.7109
Max Act: 6.0546. Min Act: -0.1700
Data Index: 1089408 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7109. Min Range: -6.7109
Max Act: 6.0546. Min Act: -0.1700
Data Index: 4670288 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7109. Min Range: -6.7109
Max Act: 6.0234. Min Act: -0.1700
Data Index: 8166719 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7109. Min Range: -6.7109
Max Act: 5.9921. Min Act: -0.1700
Data Index: 5698249 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7109. Min Range: -6.7109
Max Act: 5.9609. Min Act: -0.1700
Data Index: 4746964 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7109. Min Range: -6.7109
Max Act: 5.9609. Min Act: -0.1700
Data Index: 6910266 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7109. Min Range: -6.7109
Max Act: 5.9296. Min Act: -0.1700
Data Index: 3474923 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7109. Min Range: -6.7109
Max Act: 5.8984. Min Act: -0.1700
Data Index: 2318501 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7109. Min Range: -6.7109
Max Act: 5.8984. Min Act: -0.1700
Data Index: 1977394 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7109. Min Range: -6.7109
Max Act: 5.8671. Min Act: -0.1700
Data Index: 1951340 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7109. Min Range: -6.7109
Max Act: 5.8984. Min Act: -0.1700
Data Index: 8749848 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7109. Min Range: -6.7109
Max Act: 5.8984. Min Act: -0.1700
Data Index: 6562271 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7109. Min Range: -6.7109
Max Act: 5.8984. Min Act: -0.1700
Data Index: 8542396 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7109. Min Range: -6.7109
Max Act: 5.8984. Min Act: -0.1700
Data Index: 8166710 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7109. Min Range: -6.7109
Max Act: 5.8671. Min Act: -0.1700
Data Index: 5777413 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7109. Min Range: -6.7109
Max Act: 5.8359. Min Act: -0.1700
Data Index: 8021144 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19