Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 607 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.8113. Min Act: -0.1700
Data Index: 6423309 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.7176. Min Act: -0.1700
Data Index: 4432310 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.7176. Min Act: -0.1700
Data Index: 5064184 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.6863. Min Act: -0.1700
Data Index: 4664937 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.6551. Min Act: -0.1700
Data Index: 2676264 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.6863. Min Act: -0.1700
Data Index: 1537130 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.6238. Min Act: -0.1700
Data Index: 7540387 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.6238. Min Act: -0.1700
Data Index: 6343783 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.6238. Min Act: -0.1699
Data Index: 5433812 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.5926. Min Act: -0.1700
Data Index: 2045008 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.5926. Min Act: -0.1700
Data Index: 4133258 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.5301. Min Act: -0.1700
Data Index: 5950286 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.5613. Min Act: -0.1700
Data Index: 674029 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.5301. Min Act: -0.1700
Data Index: 6599652 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.4988. Min Act: -0.1700
Data Index: 4268087 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.4988. Min Act: -0.1700
Data Index: 2745759 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.4988. Min Act: -0.1700
Data Index: 5002796 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.4676. Min Act: -0.1699
Data Index: 5689729 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.4363. Min Act: -0.1700
Data Index: 537129 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8113. Min Range: -6.8113
Max Act: 6.4363. Min Act: -0.1700
Data Index: 5879001 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19