Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2820 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.9613. Min Act: -0.1700
Data Index: 2585353 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.8363. Min Act: -0.1700
Data Index: 8291425 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.8363. Min Act: -0.1700
Data Index: 7257487 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.7425. Min Act: -0.1700
Data Index: 759574 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.5550. Min Act: -0.1700
Data Index: 428513 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.5238. Min Act: -0.1700
Data Index: 1536911 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.4613. Min Act: -0.1700
Data Index: 3423481 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.4613. Min Act: -0.1700
Data Index: 2668824 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.4613. Min Act: -0.1700
Data Index: 7115016 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.3988. Min Act: -0.1700
Data Index: 8722384 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.4300. Min Act: -0.1700
Data Index: 3322930 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.3988. Min Act: -0.1700
Data Index: 2467508 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.3675. Min Act: -0.1700
Data Index: 4234316 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.3675. Min Act: -0.1700
Data Index: 4550093 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.3363. Min Act: -0.1700
Data Index: 5172839 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.3050. Min Act: -0.1700
Data Index: 7543298 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.3363. Min Act: -0.1700
Data Index: 6060324 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.3050. Min Act: -0.1700
Data Index: 4167541 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.2738. Min Act: -0.1700
Data Index: 7115023 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9613. Min Range: -5.9613
Max Act: 5.2425. Min Act: -0.1700
Data Index: 1238054 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19