Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1252 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.3692. Min Act: -0.1700
Data Index: 3736868 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9630. Min Act: -0.1700
Data Index: 4002368 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9005. Min Act: -0.1700
Data Index: 6988089 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.8380. Min Act: -0.1700
Data Index: 554775 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.8067. Min Act: -0.1700
Data Index: 8391900 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.7755. Min Act: -0.1700
Data Index: 2409961 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.7755. Min Act: -0.1700
Data Index: 5849446 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.8067. Min Act: -0.1700
Data Index: 714385 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.7130. Min Act: -0.1700
Data Index: 8055785 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.6817. Min Act: -0.1700
Data Index: 4657013 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.6817. Min Act: -0.1700
Data Index: 3912316 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.6505. Min Act: -0.1700
Data Index: 1605424 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.6505. Min Act: -0.1700
Data Index: 6773028 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.6192. Min Act: -0.1700
Data Index: 7412321 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.6192. Min Act: -0.1700
Data Index: 368089 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.6192. Min Act: -0.1700
Data Index: 4866519 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.5880. Min Act: -0.1700
Data Index: 8762124 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.5880. Min Act: -0.1700
Data Index: 6427094 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.5880. Min Act: -0.1700
Data Index: 1366058 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.5255. Min Act: -0.1700
Data Index: 7045851 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19