Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2621 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0355. Min Range: -5.0355
Max Act: 5.0355. Min Act: -0.1700
Data Index: 2271079 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0355. Min Range: -5.0355
Max Act: 5.0043. Min Act: -0.1700
Data Index: 1326062 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.9105. Min Act: -0.1700
Data Index: 7924852 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.9105. Min Act: -0.1700
Data Index: 296288 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.8793. Min Act: -0.1700
Data Index: 5687980 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.8793. Min Act: -0.1700
Data Index: 1764324 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.9105. Min Act: -0.1700
Data Index: 6859675 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.8480. Min Act: -0.1700
Data Index: 3830153 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.8480. Min Act: -0.1700
Data Index: 8649541 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.8480. Min Act: -0.1700
Data Index: 5516127 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.8168. Min Act: -0.1700
Data Index: 5904277 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.8168. Min Act: -0.1700
Data Index: 804761 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.7855. Min Act: -0.1700
Data Index: 3177972 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.7855. Min Act: -0.1700
Data Index: 1926603 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.7855. Min Act: -0.1700
Data Index: 1924548 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.7543. Min Act: -0.1700
Data Index: 5176603 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.7543. Min Act: -0.1700
Data Index: 2381481 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.7543. Min Act: -0.1700
Data Index: 2314746 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.7543. Min Act: -0.1700
Data Index: 8438849 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0355. Min Range: -5.0355
Max Act: 4.7543. Min Act: -0.1700
Data Index: 2887530 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19