Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2622 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.5050. Min Act: -0.1700
Data Index: 2574110 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.3800. Min Act: -0.1700
Data Index: 3831541 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.3800. Min Act: -0.1700
Data Index: 4312593 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.4113. Min Act: -0.1700
Data Index: 4352708 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.2550. Min Act: -0.1700
Data Index: 914086 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.3488. Min Act: -0.1700
Data Index: 6124138 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.3488. Min Act: -0.1700
Data Index: 4352709 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.1925. Min Act: -0.1700
Data Index: 4743935 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.1925. Min Act: -0.1700
Data Index: 4598196 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.2550. Min Act: -0.1700
Data Index: 5856043 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.1925. Min Act: -0.1700
Data Index: 836511 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.1925. Min Act: -0.1700
Data Index: 3722969 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.1300. Min Act: -0.1700
Data Index: 4790623 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.0988. Min Act: -0.1700
Data Index: 7964657 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.0675. Min Act: -0.1700
Data Index: 4312592 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.0675. Min Act: -0.1700
Data Index: 3791051 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.0363. Min Act: -0.1700
Data Index: 7291284 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.0988. Min Act: -0.1700
Data Index: 173041 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5050. Min Range: -7.5050
Max Act: 7.0363. Min Act: -0.1700
Data Index: 15182 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5050. Min Range: -7.5050
Max Act: 6.9738. Min Act: -0.1700
Data Index: 5741722 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19