Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3607 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6348. Min Range: -8.6348
Max Act: 8.6348. Min Act: -0.1700
Data Index: 3340871 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6348. Min Range: -8.6348
Max Act: 8.5723. Min Act: -0.1700
Data Index: 919818 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6348. Min Range: -8.6348
Max Act: 8.3223. Min Act: -0.1700
Data Index: 2947666 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6348. Min Range: -8.6348
Max Act: 8.2598. Min Act: -0.1700
Data Index: 3348139 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6348. Min Range: -8.6348
Max Act: 8.2598. Min Act: -0.1700
Data Index: 6472221 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6348. Min Range: -8.6348
Max Act: 8.1973. Min Act: -0.1700
Data Index: 123351 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6348. Min Range: -8.6348
Max Act: 8.1348. Min Act: -0.1700
Data Index: 5631818 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6348. Min Range: -8.6348
Max Act: 8.1348. Min Act: -0.1700
Data Index: 1008178 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6348. Min Range: -8.6348
Max Act: 8.0098. Min Act: -0.1700
Data Index: 4017933 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6348. Min Range: -8.6348
Max Act: 8.0098. Min Act: -0.1700
Data Index: 8055551 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6348. Min Range: -8.6348
Max Act: 8.0098. Min Act: -0.1700
Data Index: 7407747 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6348. Min Range: -8.6348
Max Act: 7.9473. Min Act: -0.1700
Data Index: 3315464 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6348. Min Range: -8.6348
Max Act: 7.9473. Min Act: -0.1699
Data Index: 5136364 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6348. Min Range: -8.6348
Max Act: 7.9473. Min Act: -0.1700
Data Index: 2349851 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6348. Min Range: -8.6348
Max Act: 7.9473. Min Act: -0.1700
Data Index: 2822057 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6348. Min Range: -8.6348
Max Act: 7.9473. Min Act: -0.1700
Data Index: 150084 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6348. Min Range: -8.6348
Max Act: 7.8848. Min Act: -0.1700
Data Index: 8009674 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6348. Min Range: -8.6348
Max Act: 7.8848. Min Act: -0.1700
Data Index: 6389952 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6348. Min Range: -8.6348
Max Act: 7.8848. Min Act: -0.1700
Data Index: 3315465 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6348. Min Range: -8.6348
Max Act: 7.8848. Min Act: -0.1700
Data Index: 2899610 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19