Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4393 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.4719. Min Act: -0.1700
Data Index: 4179466 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.3782. Min Act: -0.1700
Data Index: 7347169 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.3782. Min Act: -0.1700
Data Index: 3224638 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.3469. Min Act: -0.1700
Data Index: 3121282 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.3469. Min Act: -0.1700
Data Index: 8063312 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.3469. Min Act: -0.1700
Data Index: 6553236 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.3469. Min Act: -0.1700
Data Index: 1877548 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.3157. Min Act: -0.1700
Data Index: 1861976 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.3157. Min Act: -0.1700
Data Index: 6851636 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.3157. Min Act: -0.1700
Data Index: 6057039 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.2532. Min Act: -0.1700
Data Index: 7887742 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.2532. Min Act: -0.1700
Data Index: 8479249 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.2532. Min Act: -0.1700
Data Index: 2169868 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.2532. Min Act: -0.1700
Data Index: 5547348 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.2219. Min Act: -0.1700
Data Index: 3331547 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.2219. Min Act: -0.1700
Data Index: 816477 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.2219. Min Act: -0.1700
Data Index: 3278974 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.2219. Min Act: -0.1700
Data Index: 4113685 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.2219. Min Act: -0.1700
Data Index: 6117856 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4719. Min Range: -5.4719
Max Act: 5.2219. Min Act: -0.1700
Data Index: 2116504 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19