Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.9558. Min Act: -0.1700
Data Index: 4869716 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.9245. Min Act: -0.1700
Data Index: 3619290 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.7995. Min Act: -0.1700
Data Index: 8103427 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.7683. Min Act: -0.1700
Data Index: 4093851 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.7058. Min Act: -0.1700
Data Index: 8213464 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.6120. Min Act: -0.1700
Data Index: 4424901 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.5808. Min Act: -0.1700
Data Index: 5852430 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.5808. Min Act: -0.1700
Data Index: 7427300 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.4870. Min Act: -0.1700
Data Index: 6619793 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.4245. Min Act: -0.1700
Data Index: 4341528 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.4245. Min Act: -0.1700
Data Index: 2472577 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.3933. Min Act: -0.1700
Data Index: 1091867 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.3933. Min Act: -0.1700
Data Index: 3174070 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.3620. Min Act: -0.1700
Data Index: 3177476 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.2995. Min Act: -0.1700
Data Index: 5463042 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.3308. Min Act: -0.1700
Data Index: 5040017 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.3620. Min Act: -0.1700
Data Index: 2424580 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.2683. Min Act: -0.1700
Data Index: 5765088 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.2995. Min Act: -0.1700
Data Index: 6344413 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9558. Min Range: -6.9558
Max Act: 6.2995. Min Act: -0.1700
Data Index: 483429 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19