Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2070 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.6415. Min Act: -0.1700
Data Index: 4077039 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.4540. Min Act: -0.1700
Data Index: 198339 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.4540. Min Act: -0.1700
Data Index: 2386695 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.3915. Min Act: -0.1700
Data Index: 7071744 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.3915. Min Act: -0.1700
Data Index: 1500852 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.3290. Min Act: -0.1700
Data Index: 6026592 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.3290. Min Act: -0.1700
Data Index: 2982690 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.2665. Min Act: -0.1700
Data Index: 5196326 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.2665. Min Act: -0.1700
Data Index: 5992526 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.2040. Min Act: -0.1700
Data Index: 5122745 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.2665. Min Act: -0.1700
Data Index: 7759137 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.2665. Min Act: -0.1700
Data Index: 2383348 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.2665. Min Act: -0.1700
Data Index: 5174570 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.2665. Min Act: -0.1700
Data Index: 40225 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.2665. Min Act: -0.1700
Data Index: 5174581 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.2665. Min Act: -0.1700
Data Index: 6640613 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.1415. Min Act: -0.1700
Data Index: 2961115 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.1415. Min Act: -0.1700
Data Index: 6250140 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.2040. Min Act: -0.1700
Data Index: 1989056 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6415. Min Range: -9.6415
Max Act: 9.2040. Min Act: -0.1700
Data Index: 1598338 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19