Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3078 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.7669. Min Act: -0.1700
Data Index: 1202042 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.7044. Min Act: -0.1700
Data Index: 1937879 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.6419. Min Act: -0.1700
Data Index: 8172120 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.4857. Min Act: -0.1700
Data Index: 4807470 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.4232. Min Act: -0.1700
Data Index: 5849363 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.4544. Min Act: -0.1700
Data Index: 1545332 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.4232. Min Act: -0.1700
Data Index: 6398732 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.4232. Min Act: -0.1700
Data Index: 4823248 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.3919. Min Act: -0.1700
Data Index: 4027776 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.3919. Min Act: -0.1700
Data Index: 5251323 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.4232. Min Act: -0.1700
Data Index: 1665814 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.2982. Min Act: -0.1700
Data Index: 4760927 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.2982. Min Act: -0.1700
Data Index: 4750535 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.2044. Min Act: -0.1700
Data Index: 213661 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.2044. Min Act: -0.1700
Data Index: 2753244 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.2044. Min Act: -0.1700
Data Index: 8012432 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.2044. Min Act: -0.1700
Data Index: 4953571 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.2044. Min Act: -0.1700
Data Index: 2263755 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.2044. Min Act: -0.1700
Data Index: 7591118 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7669. Min Range: -7.7669
Max Act: 7.1732. Min Act: -0.1700
Data Index: 1739529 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19