Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4865 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6130. Min Range: -4.6130
Max Act: 4.6130. Min Act: -0.1700
Data Index: 8133319 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6130. Min Range: -4.6130
Max Act: 4.0817. Min Act: -0.1700
Data Index: 2751960 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6130. Min Range: -4.6130
Max Act: 4.0192. Min Act: -0.1700
Data Index: 3547824 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6130. Min Range: -4.6130
Max Act: 4.0192. Min Act: -0.1700
Data Index: 3100619 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.9879. Min Act: -0.1700
Data Index: 5125276 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.8628. Min Act: -0.1700
Data Index: 5173571 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.8316. Min Act: -0.1700
Data Index: 8818038 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.8316. Min Act: -0.1700
Data Index: 5842990 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.8316. Min Act: -0.1700
Data Index: 2736017 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.8472. Min Act: -0.1700
Data Index: 6984524 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.8159. Min Act: -0.1700
Data Index: 7438772 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.8003. Min Act: -0.1700
Data Index: 3912859 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.7690. Min Act: -0.1700
Data Index: 1132325 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.7690. Min Act: -0.1700
Data Index: 8421194 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.7847. Min Act: -0.1700
Data Index: 8252578 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.7690. Min Act: -0.1700
Data Index: 7437596 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.7377. Min Act: -0.1700
Data Index: 317513 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.7534. Min Act: -0.1700
Data Index: 2899954 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.7377. Min Act: -0.1700
Data Index: 7440092 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6130. Min Range: -4.6130
Max Act: 3.7221. Min Act: -0.1700
Data Index: 5495789 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19