Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4170 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.2719. Min Act: -0.1700
Data Index: 8485489 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.0844. Min Act: -0.1700
Data Index: 129222 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.0219. Min Act: -0.1700
Data Index: 4192447 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.0219. Min Act: -0.1700
Data Index: 1824363 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.9907. Min Act: -0.1700
Data Index: 4088152 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.9594. Min Act: -0.1700
Data Index: 6163073 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.9282. Min Act: -0.1700
Data Index: 6318723 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8969. Min Act: -0.1700
Data Index: 5190499 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8969. Min Act: -0.1700
Data Index: 8021193 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8969. Min Act: -0.1700
Data Index: 6057640 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8657. Min Act: -0.1700
Data Index: 7231151 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8657. Min Act: -0.1700
Data Index: 6821538 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8657. Min Act: -0.1700
Data Index: 3162534 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8344. Min Act: -0.1700
Data Index: 3363454 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8657. Min Act: -0.1700
Data Index: 7909081 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8344. Min Act: -0.1700
Data Index: 4689681 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8344. Min Act: -0.1700
Data Index: 1961356 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8344. Min Act: -0.1700
Data Index: 977589 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8344. Min Act: -0.1700
Data Index: 2521064 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2719. Min Range: -5.2719
Max Act: 4.8344. Min Act: -0.1700
Data Index: 5781936 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19