Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3814 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0432. Min Range: -7.0432
Max Act: 7.0432. Min Act: -0.1700
Data Index: 2149375 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.9807. Min Act: -0.1700
Data Index: 7413531 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.9494. Min Act: -0.1700
Data Index: 661804 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.9182. Min Act: -0.1700
Data Index: 6412495 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.7932. Min Act: -0.1700
Data Index: 4731961 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.6994. Min Act: -0.1700
Data Index: 5274825 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.6369. Min Act: -0.1700
Data Index: 6300239 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.6057. Min Act: -0.1700
Data Index: 5933467 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.5432. Min Act: -0.1700
Data Index: 1989357 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.5119. Min Act: -0.1700
Data Index: 139383 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.4494. Min Act: -0.1700
Data Index: 3011249 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.4807. Min Act: -0.1700
Data Index: 7428283 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.4182. Min Act: -0.1700
Data Index: 6132079 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.4182. Min Act: -0.1700
Data Index: 387164 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.3557. Min Act: -0.1700
Data Index: 5807098 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.3869. Min Act: -0.1700
Data Index: 2901406 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.3869. Min Act: -0.1700
Data Index: 4612600 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.3869. Min Act: -0.1700
Data Index: 337708 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.3869. Min Act: -0.1700
Data Index: 4839381 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0432. Min Range: -7.0432
Max Act: 6.3557. Min Act: -0.1700
Data Index: 2235616 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19