Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4821 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.9218. Min Act: -0.1700
Data Index: 5468419 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.7968. Min Act: -0.1700
Data Index: 7041652 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.7655. Min Act: -0.1700
Data Index: 304445 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.6093. Min Act: -0.1700
Data Index: 229164 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.5780. Min Act: -0.1700
Data Index: 5977363 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.5468. Min Act: -0.1700
Data Index: 4287396 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.5468. Min Act: -0.1700
Data Index: 704743 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.5468. Min Act: -0.1700
Data Index: 7396556 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.5468. Min Act: -0.1700
Data Index: 4119803 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.5155. Min Act: -0.1700
Data Index: 3877818 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.5155. Min Act: -0.1700
Data Index: 2874779 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.5155. Min Act: -0.1700
Data Index: 191953 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.4843. Min Act: -0.1700
Data Index: 5096517 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.5155. Min Act: -0.1700
Data Index: 2498825 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.4530. Min Act: -0.1700
Data Index: 1113850 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.4530. Min Act: -0.1700
Data Index: 900380 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.4218. Min Act: -0.1700
Data Index: 2523684 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.4218. Min Act: -0.1700
Data Index: 7551895 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.4218. Min Act: -0.1700
Data Index: 8642249 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9218. Min Range: -5.9218
Max Act: 5.3593. Min Act: -0.1700
Data Index: 8058561 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19