Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3227 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.5190. Min Act: -0.1700
Data Index: 3230150 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.5190. Min Act: -0.1700
Data Index: 3490356 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.3315. Min Act: -0.1700
Data Index: 1153083 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.3315. Min Act: -0.1700
Data Index: 57810 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.3315. Min Act: -0.1700
Data Index: 4511798 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.2377. Min Act: -0.1700
Data Index: 7542447 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.2377. Min Act: -0.1700
Data Index: 6758048 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.1752. Min Act: -0.1700
Data Index: 1238423 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.2065. Min Act: -0.1700
Data Index: 7783462 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.1752. Min Act: -0.1700
Data Index: 7340350 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.2065. Min Act: -0.1700
Data Index: 8082981 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.1440. Min Act: -0.1700
Data Index: 8433276 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.1127. Min Act: -0.1700
Data Index: 4511785 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.0815. Min Act: -0.1700
Data Index: 6767895 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.1127. Min Act: -0.1700
Data Index: 4511784 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.0815. Min Act: -0.1700
Data Index: 1145216 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.1127. Min Act: -0.1700
Data Index: 2861806 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.0190. Min Act: -0.1700
Data Index: 243428 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5190. Min Range: -6.5190
Max Act: 6.0190. Min Act: -0.1700
Data Index: 1956159 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5190. Min Range: -6.5190
Max Act: 5.9565. Min Act: -0.1700
Data Index: 4689832 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19