Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3784 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6199. Min Range: -6.6199
Max Act: 6.6199. Min Act: -0.1700
Data Index: 4514532 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6199. Min Range: -6.6199
Max Act: 6.3386. Min Act: -0.1700
Data Index: 2535893 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6199. Min Range: -6.6199
Max Act: 6.3386. Min Act: -0.1700
Data Index: 8733271 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.9011. Min Act: -0.1700
Data Index: 3070952 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.9011. Min Act: -0.1700
Data Index: 8143732 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.8699. Min Act: -0.1700
Data Index: 1545302 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.8074. Min Act: -0.1700
Data Index: 7387508 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.7761. Min Act: -0.1700
Data Index: 8669964 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.8074. Min Act: -0.1700
Data Index: 1992215 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.8074. Min Act: -0.1700
Data Index: 3670702 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.7449. Min Act: -0.1700
Data Index: 7685203 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.7136. Min Act: -0.1700
Data Index: 6737726 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.7449. Min Act: -0.1700
Data Index: 3344916 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.7136. Min Act: -0.1700
Data Index: 2827825 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.6511. Min Act: -0.1700
Data Index: 1722700 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.6511. Min Act: -0.1700
Data Index: 2803896 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.6199. Min Act: -0.1700
Data Index: 1069677 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.6199. Min Act: -0.1700
Data Index: 3682684 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.6199. Min Act: -0.1700
Data Index: 5831925 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6199. Min Range: -6.6199
Max Act: 5.5886. Min Act: -0.1700
Data Index: 6638213 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19