Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 48 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.5937. Min Act: -0.1700
Data Index: 6764474 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5937. Min Range: -6.5937
Max Act: 6.2499. Min Act: -0.1700
Data Index: 7079854 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.8749. Min Act: -0.1700
Data Index: 8621869 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.7812. Min Act: -0.1700
Data Index: 6198515 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.7187. Min Act: -0.1700
Data Index: 2751071 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.7187. Min Act: -0.1700
Data Index: 5293968 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.6874. Min Act: -0.1700
Data Index: 7603763 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.6874. Min Act: -0.1700
Data Index: 6658921 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.6874. Min Act: -0.1700
Data Index: 5618440 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.6874. Min Act: -0.1700
Data Index: 8177019 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.6562. Min Act: -0.1700
Data Index: 769949 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.6562. Min Act: -0.1700
Data Index: 7682802 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.6562. Min Act: -0.1700
Data Index: 6848819 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.5937. Min Act: -0.1700
Data Index: 4938214 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.5937. Min Act: -0.1700
Data Index: 1052845 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.5937. Min Act: -0.1700
Data Index: 5523571 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.5624. Min Act: -0.1700
Data Index: 5252275 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.5624. Min Act: -0.1700
Data Index: 7309859 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.5312. Min Act: -0.1700
Data Index: 7910539 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5937. Min Range: -6.5937
Max Act: 5.5312. Min Act: -0.1700
Data Index: 3793583 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19