Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2713 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.9545. Min Act: -0.1700
Data Index: 1188771 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.9545. Min Act: -0.1700
Data Index: 7409201 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.9545. Min Act: -0.1700
Data Index: 7908464 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.8920. Min Act: -0.1700
Data Index: 7883881 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.8295. Min Act: -0.1700
Data Index: 4399744 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.8295. Min Act: -0.1700
Data Index: 8565941 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.8295. Min Act: -0.1700
Data Index: 6137089 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.7670. Min Act: -0.1700
Data Index: 4487534 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.7045. Min Act: -0.1700
Data Index: 628914 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.7045. Min Act: -0.1700
Data Index: 7243876 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.6420. Min Act: -0.1700
Data Index: 563823 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.7045. Min Act: -0.1700
Data Index: 3768699 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.7045. Min Act: -0.1700
Data Index: 3779341 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.7045. Min Act: -0.1700
Data Index: 7500881 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.6420. Min Act: -0.1700
Data Index: 4633774 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.6420. Min Act: -0.1700
Data Index: 3055474 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.7045. Min Act: -0.1700
Data Index: 4144854 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.6420. Min Act: -0.1700
Data Index: 4193006 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.5795. Min Act: -0.1700
Data Index: 661553 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9545. Min Range: -9.9545
Max Act: 9.5795. Min Act: -0.1700
Data Index: 1020841 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19