Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2423 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.7235. Min Act: -0.1700
Data Index: 1806298 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.4110. Min Act: -0.1700
Data Index: 480540 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.3485. Min Act: -0.1700
Data Index: 8464968 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.1922. Min Act: -0.1700
Data Index: 6550752 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.0984. Min Act: -0.1700
Data Index: 7044649 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.0984. Min Act: -0.1700
Data Index: 80191 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.1297. Min Act: -0.1700
Data Index: 851818 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.0359. Min Act: -0.1700
Data Index: 5937194 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.0359. Min Act: -0.1700
Data Index: 563780 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.0047. Min Act: -0.1700
Data Index: 2707512 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.0047. Min Act: -0.1700
Data Index: 3983846 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.0047. Min Act: -0.1700
Data Index: 5045641 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7235. Min Range: -4.7235
Max Act: 3.9734. Min Act: -0.1700
Data Index: 4534526 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.0047. Min Act: -0.1700
Data Index: 132921 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.0047. Min Act: -0.1700
Data Index: 2871699 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.0047. Min Act: -0.1700
Data Index: 7095703 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7235. Min Range: -4.7235
Max Act: 3.9734. Min Act: -0.1700
Data Index: 7468928 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7235. Min Range: -4.7235
Max Act: 3.9734. Min Act: -0.1700
Data Index: 2774167 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7235. Min Range: -4.7235
Max Act: 3.9734. Min Act: -0.1700
Data Index: 3011578 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7235. Min Range: -4.7235
Max Act: 3.9734. Min Act: -0.1700
Data Index: 1454336 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19