Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3952 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1161. Min Range: -8.1161
Max Act: 8.1161. Min Act: -0.1700
Data Index: 1444871 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.7411. Min Act: -0.1700
Data Index: 8768599 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.6786. Min Act: -0.1700
Data Index: 7272692 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.5848. Min Act: -0.1700
Data Index: 2512428 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.4598. Min Act: -0.1700
Data Index: 8807942 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.3661. Min Act: -0.1700
Data Index: 1225250 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.3348. Min Act: -0.1700
Data Index: 4848217 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.3348. Min Act: -0.1700
Data Index: 4869392 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.2098. Min Act: -0.1700
Data Index: 4033450 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.2098. Min Act: -0.1700
Data Index: 4190460 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.1473. Min Act: -0.1700
Data Index: 2250277 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.1473. Min Act: -0.1700
Data Index: 5457757 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.1473. Min Act: -0.1700
Data Index: 7864668 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.0848. Min Act: -0.1700
Data Index: 7272700 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.0536. Min Act: -0.1700
Data Index: 6243412 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.0223. Min Act: -0.1700
Data Index: 6813692 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.0223. Min Act: -0.1700
Data Index: 7288631 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1161. Min Range: -8.1161
Max Act: 7.0223. Min Act: -0.1700
Data Index: 6713755 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1161. Min Range: -8.1161
Max Act: 6.9911. Min Act: -0.1700
Data Index: 1360847 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1161. Min Range: -8.1161
Max Act: 6.9911. Min Act: -0.1700
Data Index: 4275038 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19