Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4734 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.8803. Min Act: -0.1700
Data Index: 6591924 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.8177. Min Act: -0.1700
Data Index: 2607610 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.7708. Min Act: -0.1700
Data Index: 6142308 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.7552. Min Act: -0.1700
Data Index: 7736230 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.7552. Min Act: -0.1700
Data Index: 8696211 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.7395. Min Act: -0.1700
Data Index: 5482578 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.7239. Min Act: -0.1700
Data Index: 1461653 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.7082. Min Act: -0.1700
Data Index: 6741682 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.7082. Min Act: -0.1700
Data Index: 5489136 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.7082. Min Act: -0.1700
Data Index: 1317419 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.7082. Min Act: -0.1700
Data Index: 2269497 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6926. Min Act: -0.1700
Data Index: 692660 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6926. Min Act: -0.1700
Data Index: 5557315 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6770. Min Act: -0.1700
Data Index: 5675391 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6770. Min Act: -0.1700
Data Index: 6299761 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6613. Min Act: -0.1700
Data Index: 5397390 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6613. Min Act: -0.1700
Data Index: 2954821 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6613. Min Act: -0.1700
Data Index: 5576620 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6613. Min Act: -0.1700
Data Index: 696854 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8803. Min Range: -3.8803
Max Act: 3.6300. Min Act: -0.1700
Data Index: 4491393 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19