Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1487 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 1877818 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 546111 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 2744439 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 658411 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 859600 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 3117087 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 586102 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 2339059 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 3529780 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 2613589 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 968331 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 1116858 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 3565608 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 750002 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 3509592 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 792545 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 2235139 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 1070665 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 2670470 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3360. Min Range: -3.3360
Max Act: 3.3360. Min Act: -0.1700
Data Index: 3270438 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19