Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2951 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.9311. Min Act: -0.1700
Data Index: 6289924 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.8374. Min Act: -0.1700
Data Index: 2888662 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.8374. Min Act: -0.1700
Data Index: 7420604 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.8374. Min Act: -0.1700
Data Index: 6572268 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.8686. Min Act: -0.1700
Data Index: 3249443 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.8374. Min Act: -0.1700
Data Index: 6387702 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.8686. Min Act: -0.1700
Data Index: 4683762 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.8061. Min Act: -0.1700
Data Index: 2558511 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.7436. Min Act: -0.1700
Data Index: 443198 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.7124. Min Act: -0.1700
Data Index: 2212712 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6811. Min Act: -0.1700
Data Index: 1329101 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6811. Min Act: -0.1700
Data Index: 7837370 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6186. Min Act: -0.1700
Data Index: 3902527 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6499. Min Act: -0.1700
Data Index: 204242 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6499. Min Act: -0.1700
Data Index: 7875135 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6499. Min Act: -0.1700
Data Index: 3147193 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6499. Min Act: -0.1700
Data Index: 5875559 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6186. Min Act: -0.1700
Data Index: 690291 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6186. Min Act: -0.1700
Data Index: 3353329 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6499. Min Act: -0.1700
Data Index: 551192 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19